STUDY ON IMPACT OF PREDICTIVE

ANALYTICS FOR MARKETER’S ENGAGING

PERFORMANCE AFTER THE PANDEMIC
Submitted in partial fulfillment of the requirements for the award of

MASTER OF BUSINESS ADMINISTRATION

by

DAISY BOSCO.T
Register No.40410038

SCHOOL OF MANAGEMENT STUDIES

SATHYABAMA
INSTITUTE OF SCIENCE AND TECHNOLOGY

(DEEMED TO BE UNIVERSITY)
Accredited with Grade “A” by NAAC I 12B Status by UGC I Approved by AICTE

JEPPIAAR NAGAR, RAJIV GANDHI SALAI, CHENNAI - 600 119

APRIL 2022
 SATHYABAMA
INSTITUTE OF SCIENCE AND TECHNOLOGY
(DEEMED TO BE UNIVERSITY)
Accredited with “A” grade by NAAC I 12B Status by UGC I Approved by AICTE
Jeppiaar Nagar, Rajiv Gandhi Salai, Chennai - 600119
www.sathyabama.ac.in

SCHOOL OF MANAGEMENT STUDIES

BONAFIDE CERTIFICATE

This is to certify that this Project Report is the bonafide work DAISY BOSCO. T
40410038 who carried out the project entitled “Study on Impact of Predictive
Analytics for Marketer’s Engaging Performance After the Pandemic” under my
supervision from January 2022 to March 2022.

Dr. John Paul M, Associate Professor

Internal guide

Dr. BHUVANESWARI. G
Dean – School of Management Studies

Submitted for Viva voce Examination held on_____________________

Internal Examiner External Examiner

 DECLARATION

I DAISY BOSCO. T (40410038) hereby declare that the Project Report

entitled “Study on Impact of Predictive Analytics for Marketer’s
Engaging Performance After the Pandemic” done by me under the
guidance of Dr. John Paul M, Associate Professor is submitted in
partial fulfillment of the requirements for the award of Master of Business
Administration degree.

DATE:

PLACE: DAISY BOSCO. T

 ACKNOWLEDGEMENT

I am pleased to acknowledge my sincere thanks to Board of Management of

SATHYABAMA for their kind encouragement in doing this project and for
completing it successfully. I am grateful to them.

I convey my sincere thanks to Dr. G. Bhuvaneswari, Dean - School of

Management Studies and Dr. A. Palani, Head - School of Management
Studies for providing me necessary support and details at the right time during
the progressive reviews.

I would like to express my sincere and deep sense of gratitude to my Project

Guide Dr. John Paul M, Associate Professor for her valuable guidance,
suggestions and constant encouragement paved way for the successful
completion of my project work.

I wish to express my thanks to all Teaching and Non-teaching staff members of

the School of Management Studies who were helpful in many ways for the
completion of the project.

DAISY BOSCO. T
TABLE OF CONTENTS

CHAPTER TITLE PAGE NO

NO.

ABSTRACT I

LIST OF TABLES Ii

LIST OF CHARTS Iii

INTRODUCTION

1.1 Introduction

1.2 Industry Profile

1
1.3 Problem Statement

1.4 Need for the Study

1.5 Scope and Significance of Study

1.6 Objectives of the Study

1.7 Limitations of the Study

2 LITERATURE REVIEW

RESEARCH METHODOLOGY

3.1 Research Design

3.2 Sampling Technique

3 3.3 Sources of Data

3.4 Structure of Questionnaire

3.5 Sample Size

3.6 Hypothesis / Analytical Tools

4 DATA ANALYSIS AND INTERPRETATION

4.1 Percentage Analysis

4.2 Hypothesis Testing

5 FINDINGS, SUGGESTIONS AND CONCLUTION

5.1 Findings

5.2 Suggestions

5.3 Conclusion

REFERENCES

APPENDIX (Questionnaire)
 ABSTRACT

This study focuses on the public's view of predictive analytics and marketing
interaction with it. Predictive analytics is a sort of digital marketing data analysis that
uses the appropriate technology. Rather than merely knowing what has happened,
the objective is to make the best prediction of what will happen in the future. It is a
statistical strategy that combines data mining, predictive modelling, and machine
learning to estimate the likelihood of a future occurrence based on current and
previous data. Customer and audience segmentation allow you to segment your
audience based on their behavior, demographics, firmographics, interests, or any
other element in predictive analytics. Companies are presently dealing with a flood
of data originating from transactional databases, equipment log files and media files,
sensors, and other data sources. A business expert can construct a cross-selling
model based on current customer data that forecasts what additional things they are
likely to buy from the same company in the future. Digital marketing is the promotion
of brands using the internet and other types of digital communication in order to
interact with potential customers. The tools can investigate "expect to purchase" by
assessing consumer behavior using historical and current data to identify persons
whose data fits ideal consumers. To stay within or optimize your budget, work with
vendors and publishers for online paid channels, and negotiate with stakeholders
wherever feasible.
 LIST OF TABLES

Table No Particulars Page no

1 Age of the Respondents
2 Gender of the Respondents
3 Educational Qualification of the Respondents
4 Marital Status of the respondents
5 Occupation of the respondents
6 Annual income of the respondents
7 Awareness on Digital Marketing Sources
8 Kinds of Digital Marketing Sources
9 Predictive Analytics’s Preference
10 Predictive analytics Technique
11 Predictive Analytics Model
12 Predictive Analytics Tools
13 Predictive Analytics Problems
14 Decision Making using Predictive Analytics Report
15 Digital Marketing Strategy
16 Digital Marketing Tools
17 Customer’s Preference on Digital Marketing
18 Customer’s Satisfaction Level on Digital Marketing
19 Rate Customer Satisfaction Towards Digital Marketing
20 Digital Marketing Fraud
21 Digital Fraud Impact
22 Digital Fraud Prevention
23 Why Predictive Analytics
24 Will You Suggest Predictive Analytics
 LIST OF CHARTS

Chart No Particulars Page no

1 Age of the Respondents
2 Gender of the Respondents
3 Educational Qualification of the Respondents
4 Marital Status of the respondents
5 Occupation of the respondents
6 Annual income of the respondents
7 Awareness on Digital Marketing Sources
8 Kinds of Digital Marketing Sources
9 Predictive Analytics’s Preference
10 Predictive analytics Technique
11 Predictive Analytics Model
12 Predictive Analytics Tools
13 Predictive Analytics Problems
14 Decision Making using Predictive Analytics Report
15 Digital Marketing Strategy
16 Digital Marketing Tools
17 Customer’s Preference on Digital Marketing
18 Customer’s Satisfaction Level on Digital Marketing
19 Rate Customer Satisfaction Towards Digital Marketing
20 Digital Marketing Fraud
21 Digital Fraud Impact
22 Digital Fraud Prevention
23 Why Predictive Analytics
24 Will You Suggest Predictive Analytics
 CHAPTER – 1
INTRODUCTION

1.1 INTRODUCTION
This is a study on impact of predictive analytics for marketer’s engaging
performance after the pandemic. The study is based on the marketer’s current
engaging performance in predictive analytics. Predictive analytics is a type of digital
marketing data that is examined with the appropriate digital marketing technologies.
Predictive analytics employs machine learning or statistics to forecast future events
ranging from sales trends to customer involvement patterns. Predictive analytics
can be used in marketing across a variety of touchpoints, from brand awareness
through post-purchase activity. The purpose is to provide the best judgement of
what will happen in the future, rather than simply knowing what has happened.

Predictive analytics is a type of advanced analytics that makes predictions about

future events using historical data, data analysis, data mining tools, and machine
learning. Businesses employ predictive analytics to detect data trends and identify
threats and opportunities. Predictive analytics is the practice of employing a
combination of statistical methodologies such as data mining, predictive modelling,
and machine learning to determine the likelihood of a future event based on current
and previous data. Credit scoring is one of the first and most visible applications of
predictive analytics in the corporate world. It encompasses a variety of statistical
approaches such as data mining, predictive modelling, and machine learning, which
examine current and historical data in order to make predictions about future or
otherwise unknown events.

Predictive analytics is a term used in marketing to describe the use of current and/or
historical data combined with statistical approaches to estimate the possibility of a
future event. When a prospect meets a specific threshold in your lead scoring
methodology, you may utilize the data to activate appropriate marketing and
prioritize your sales outreach efforts, depending on your business model.
1.2 INDUSTRY PROFILE
Predictive analytics functions are used to forecast future trends and provide
recommendations for how businesses should adjust their marketing plans and
strategies in response to these trends. Data, statistical algorithms, and machine
learning techniques are used in predictive analytics to determine the likelihood of
future outcomes based on historical data. In predictive analytics, customer and
audience segmentation lets you determine whether you should segment your
audience based on their behavior, demographics, firmographics, interests, or any
other criteria. We can utilize your client data to build identifications if you want to
take your segmentation a step further. In practice, this means identifying and
targeting prospects who are similar to your current customers in some way. In
practice, the process boils down to ranking identified prospects depending on their
likelihood of converting based on previous customer data. While we may believe
that larger organizations take longer to complete a purchase than smaller
businesses, this is not necessarily the case. In the report, predictive analytics will
not make any decisions. It is your responsibility to analyses the data and turn it into
valuable information. We can then direct our marketing and sales efforts toward
those prospects in the hope of converting them before the deadline.

Predictive analytics is a sort of advanced data analytics that examines past data
behavior and projects data-driven insights as future outcomes. Predictive analytics
is widely employed in today's industries, including healthcare, life sciences, oil and
gas, insurance, and so on, and it provides the most accurate predictions when
business plans and applications are well-defined. Companies are currently coping
with a deluge of data from transactional databases, equipment log files and media
files, sensors, and other data sources. Data analysts use predictive analytics to
analyses this data in order to gain insights and make predictions about future
events.

Unified Marketing Measurement (UMM) is a marketing analytics strategy that

combines attribution models' aggregate data and insights into a single holistic
measurement. This model can be created based on the context of what needs to be
predicted, utilizing the same data that was obtained for data mining. The fresh data
is incorporated into models to forecast future outcomes once the model has been
developed. A business expert, for example, can use current customer data to create
a cross-selling model that predicts what other goods they are likely to buy from the
same company.

Data Mining (DM) is the process of predicting outcomes by looking for anomalies,
patterns, and correlations in huge data sets. You may use this information to
enhance sales, lower costs, strengthen customer connections, reduce risks, and
more using a variety of approaches. Data mining aims to manage vast amounts of
organized or unstructured data sets in order to uncover hidden patterns and
relationships among variables presented. These associations can be utilized to
understand the behavior of the event from which data is compiled once they've been
recognized.

Machine Learning (ML) is a type of artificial intelligence (AI) that enables software
applications to increase prediction accuracy without being specifically designed to
do so. Machine learning algorithms use historical data as input to forecast new
output values. Iterative methods and techniques in machine learning can be used
to find patterns in large data sets and construct models. Recommendation engines,
for example, are widely used for online purchasing recommendations since they
create predictions based on previous purchases and browsing behavior of
consumers.

The promotion of brands using the internet and other forms of digital communication
in order to engage with potential customers is known as digital marketing. This
encompasses not only email, social media, and web-based advertising, but also text
and multimedia messaging as a marketing medium. Predictive analytics solutions
could help segment marketing leads by displaying adverts on websites and social
media platforms depending on customer behavior and interests. The tools can look
into "expect to purchase" by analyzing consumer behavior based on prior and
current data to find people whose data matches ideal customers. The use of the
internet, mobile devices, social media, search engines, display advertising, and
other platforms to reach consumers is known as digital marketing.
Marketers could also use predictive analytics for lead scoring by analyzing data to
determine which prospects are potentially most valuable to the company, or to
determine how likely prospective consumers are to buy products or services and
plan how and with what information they should be contacted. Sales and promotion
timing have become an art form, with predictive analytics applied to customer,
inventory, and historical sales data providing appropriate circumstances/time for
price reductions or increases.

A marketer is someone who works in the marketing department. A person whose

major responsibility it is to handle a product's or company's marketing resources. It
all starts with in-depth understanding of the sector. Many of the qualities of a
successful performance marketing manager begin with proactive study and
education about industry trends. Marketers' performance never stops learning since
they gain from skill advancement. They are in charge of determining the long-term
strategic direction of numerous marketing channels. Finally, before launching any
form of campaign, they must be confident in leading and driving a strategy.
Marketers must interact and collaborate across teams and levels of the company to
lead, manage, and work closely with all internal and external teams in predictive
analytics. The marketer should define objectives and then report to management or
direct to keep them up to date on the campaign's progress. He or she should work
with creative teams to create campaign designs and creative materials that are
channel-appropriate. To stay within budget or optimize budget, coordinate with
vendors and publishers for online paid channels, and negotiate with stakeholders
where possible.

1.3 PROBLEM STATEMENT

We spend a lot of time discussing how predictive analytics may help us make better
business decisions, but we must equally realize that there are a few things that can
go wrong. I've found a few issues that I'd like to bring to your attention in the future,
based on my research.

➢ Optimizing Promotion Opportunities as well as determining Customer

Response in the Predictive Analytics.
 ➢ To deduct the efficient Fraud identity in the Digital World with available
predictive analytics tools.

1.4 NEED FOR THE STUDY

The study's primary goal is to determine predictive analytics performance. This

research identifies and analyzes a marketer's level of involvement in digital
marketing. It also helps in understanding the methods used in B2B predictive
analytics. The report also identifies the most important technologies because they
allow marketers to respond on data in real time while presenting dynamic content
automatically. In today's world, this is mostly focused on maximizing promotion
opportunities as well as identifying and preventing fraud. To concentrate on the
digital marketing models.

1.5 SCOPE AND SIGNIFICANCE OF STUDY

The importance of my project is to use Predictive Analytics to raise brand recognition

for After Sales Service (ASS) in digital marketing. Data mining and machine learning
are used in predictive analytics to incorporate the insights gained from multiple
datasets, algorithms, and models to forecast future behavior. Predictive analytics
uses digital marketing tools to forecast future events. In the digital environment, to
make better media planning and purchase decisions. Predictive analytics will be
used to detect and prevent fraud in the digital world.

1.4 OBJECTIVES OF THE STUDY

• To identify the Marketers performance in Predictive Analytics

• To know the Current Engaging tools of Predictive Analytics by Marketers
• To determine the digital marketing tools in B2B
• To optimize Brand awareness to After Sales Service
• To estimate the benefit of outcome of the digital marketing
• To spot the Frauds in digital marketing
1.7 LIMITATIONS OF THE STUDY

The sample data for my study needs the responds from the marketers and business
people, since limited to an extent because it was little difficult to find the targeted
people.

➢ People were not comfortable to disclose the tools and techniques that are
used by them for their organization/project report.
➢ Predictive analytics is a sort of analytics in which improving the operational
efficiency of one area of business might lead to unfair results.
 CHAPTER – 2
REVIEW OF LITERATURE

Galit Shmueli and Otto R. Koppius, 2011 Predictive analytics in information

systems research. This research paper emphasizes the importance of incorporating
predictive analytics into information systems research and provides various real
examples of how to do so. Despite their importance, predictive analytics are rarely
discussed in empirical IS research. To demonstrate the fundamental differences
between predictive analytics and explanatory statistical modelling, we demonstrate
how they differ at each stage of the modelling process. These distinctions result in
various end models, with a pure explanatory statistical model best suited to
evaluating causal hypotheses and a pure predictive model best suited to predicting
predictive power. To demonstrate these contrasts and show how predictive analytics
may bring theoretical and practical value to IS research, we turn a well-known
explanatory paper on TAM into a predictive context.

Piotr Tarka and Maciej Łobiński, 2014 Decision Making in Reference to Model of
Marketing Predictive Analytics – Theory and Practice. Predictive analytics are the
tools employed in this study, and they contain procedures specified by well-known
rules coming from the domains of econometrics and statistics, which include
components of forecasting, modelling, and simulation. In reality, they do their best
to put them to use in order to better understand and adapt future interactions with
consumers, plan better product and pricing levels, and choose appropriate
distribution channels. Such businesses do not let such opportunities pass them by.
As a result, we expect their interest in pursuing marketing-mix using predictive
analytical models to increase rather than decrease.

Poornima. S and Pushpalatha. M, 2018 A survey of predictive analytics using big

data with data mining. Predictive analytics for the business and medical industries
are already employed in this survey document. Predictive analytics employs
datamining techniques to make predictions about future events, which are
subsequently used to generate recommendations. The technique entails a historical
data analysis, followed by a prediction of future events based on that review. Affinity
analysis, in addition to classification and prediction, is one of the analytical
approaches utilized in predictive analytics. Also mentioned were the techniques and
algorithms, as well as the issues that arise when using big data. As a result, an
unique technique or model for predicting could be developed using predictive
analytics modelling methodologies suitable for big data.

Vaibhav Kumar and M. L. Garg, 2018 Predictive Analytics: A Review of Trends

and Techniques. This study paves the way for the development of new predictive
analytics algorithms. Predictive models have a long history of being used for
prediction tasks. Previously, statistical models were employed as predictive models,
and these models were based on sample data from a huge data collection. The
introduction of intelligent computation techniques and algorithms has transformed
the world of computation due to advances in artificial intelligence and machine
learning. Machine learning models have a long history of success when utilized as
prediction models. In the realm of predictive analytics, artificial neural networks
ushered in a revolution. Any value's output or future can be anticipated based on
the input parameters.

Suryadi Tanuwijaya, Andry Alamsyah and Maya Ariyanti, 2021 Mobile Customer
Behavior Predictive Analysis for Targeting Netflix Potential Customer. In this survey,
we'll talk about how predictive analysis based on mobile consumer behavior data
may be used to help mobile operators' daily operations, such as marketing and sales
targeting to potential customers. It is predicted that by using this strategy, campaign
costs will be lowered and the proper product will be sent to the right client. Aside
from Netflix, the same concept can be applied to any other VOD platform.

Kasereka Henrys, 2021 Role of Predictive Analytics in Business. This research is

about Predictive analytics is a multidisciplinary study field. It's a group of
technologies that work together to figure out what's hidden in data and forecast the
future. Maintaining a competitive advantage has become a necessary corporate
activity. The relevance of predictive analytics in business is critical for survival, as
evidenced by the various scenarios presented. In fact, competitiveness is quite high,
and each firm must be prepared and have appropriate predictive information on
which to make its judgments.

Bharati M. Ramager, 2010 Data Mining Techniques and Applications. This paper
examines a few data mining approaches, algorithms, and some of the corporations
that have successfully implemented data mining technologies to better their
businesses. Data mining has a wide range of applications in practically any industry
that generates data, which is why it is regarded as one of the most important
frontiers in database and information systems, as well as one of the most promising
multidisciplinary advances in Information Technology.

Aurangzeb Khan, Baharum Baharudin, Lam Hong Lee and Khairullah khan,
2010 A Review of Machine Learning Algorithms for Text-Documents Classification.
With a focus on text representation and machine learning techniques, the purpose
of this study is to demonstrate the fundamental concepts and methodology used in
text document categorization while also increasing awareness of some of the
exciting challenges that remain to be solved. For a more accurate categorization
procedure, develop and examine feature selection approaches. To reduce classifier
training and testing time while enhancing classification precision, recall, and
accuracy. The use of semantics and ontology to classify documents and retrieve
information. As a result, further online data, integration, and schema matching study
is necessary.

Teng Xiuyi, Gong Yuxia, 2018 Research on Application of Machine Learning in

Data Mining. The definition, model, development stage, classification, and
commercial application of machine learning are all discussed in this study, with a
focus on machine learning's function in data mining. Understanding the various
machine learning approaches aids in selecting the most appropriate strategy for a
given application. As a result, this study outlines and analyses machine learning
technology, as well as its benefits and drawbacks in data mining. Machine learning
technology in data mining has been used in a variety of industries, including the
financial, retail, insurance, and telecommunications industries. When using data
mining technologies, businesses should be aware of the benefits and drawbacks of
various technologies and processes, and choose the best technology for the
environment and task at hand.

James Cannella, 2018 Artificial Intelligence in Marketing. The era of AI Marketing

is soon approaching, according to this study, and it will have far-reaching
ramifications. In an AI-powered workplace, an individual's awareness of their role in
creating and sharing value is critical not only to their own success, but also to the
success of their firm. Despite the major difficulties that must be resolved before
widespread use, artificial intelligence provides enormous benefits to marketers,
consumers, and society at large by enabling marketers to generate and distribute
value at scale to the right people at the right time in the right way. Fundamental
changes to the way marketers communicate with clients, the techniques and tools
they employ to achieve their goals, the types of abilities that are valued in the
workplace, and the nature of their day-to-day responsibilities are all part of the AI
Marketing Era.

Shangran Li, 2019 Research on Data Mining Technology Based on Machine

Learning Algorithm. In this paper, a high-performance machine learning-based
method for mobile terminal location in an outdoor network is proposed. It has higher
accuracy and reduced processing complexity than standard approaches.
Classification, regression analysis, association rules, and clustering are the most
common data mining tasks. The practice shows that using a machine learning-
based positioning method increases positioning accuracy and saves time
complexity.

Dipti Theng and Mahesh Theng, 2020 Machine Learning Algorithms for Predictive
Analytics: A Review and New Perspectives. Predictive analytics employing machine
learning and their applications on real-world datasets were presented in this study.
Various research efforts on predictive analytics utilizing machine learning
approaches are discussed, with future scope for further extension listed. Three of
the most common machine learning approaches in predictive analytics are applied,
and a comparison of their performance indicators is offered. SVM beat the other
learning algorithms in terms of accuracy and precision, according to the testing
results. SVM-based predictive analytics can be applied to a variety of real-world
issues, including classification and regression analysis. Many studies on kernel
functions have been conducted in order to improve SVM performance.

Tim Ambler and Flora Kokkinaki, 2000 Marketing Performance Measurement:

Which Way is Up. The research given in this article looks into the measurement of
marketing performance in a variety of industries. Although changes in the principal
marketing asset must be taken into account when evaluating marketing
performance, few organizations specifically analyses brand equity for this reason.
Marketers, according to the studies thus far, need to be more precise about what
they intend to achieve and improve their representation of their progress toward
those goals. Marketers, on the other hand, are in charge of making sure that
performance is properly evaluated. Unless they organize the exams in accordance
with their own marketing plan, they may expect to be rated harshly by other
managers using other criteria.

Paweł Cichosz, 2011 Assessing the Quality of Classification Models: Performance

Measures and Evaluation Procedures. This article provides a thorough examination
of methods for evaluating classification models, as well as recommendations for
their successful implementation. Their common purpose is to assess model
generalisation capabilities, which are important in establishing the applicability and
usability of classification and other data mining models. The main contribution of this
paper is a detailed examination of existing classifier evaluation methodologies that
are specifically adapted to the most common practical applications. The
classification approach and dataset properties, as well as the computational
resources available for model evaluation, which can be computationally demanding
for large datasets, all influence the optimal option.

Kamaldeep Kaur, Rattan Datta and Sunil Kumar Khatri, 2014 Analysis of various
testing techniques. This study investigates whether mutation testing could be a
useful addition to the testing procedure. If it is to be cost-effective, it is time-
consuming and requires the use of tools. If we are to be confidence in the results,
we must utilize a large number of mutants to improve Residual Defect Density
estimations. Object Orientation has a wide range of structural and operational
changes that are specific to objects. Tools like mu-Java take advantage of Java's
features to make mutant production and testing more efficient. Even with excellent
techniques, huge numbers of mutations might take a long time to execute.

Nick Phelps and Sophia Christakis, 2018 The Current State of Marketing
Measurement and Optimization. This study is predicated on Marketers must change
their approach from passively examining post-campaign data to actively evaluating
results in order to influence future tactics. Growing privacy concerns, as well as the
prospect of new norms and regulations, emphasize the importance of properly
maintaining this information and establishing agreement to its usage. Some
companies have already realized this and are gaining an advantage over their
competitors. To supplement the quantitative study, five qualitative interviews were
performed, all of which matched the same criteria as the online survey.
Respondents were given a little gift as a thank you for their time.

Quinlan. J. R, 1986 Induction of Decision Trees. The purpose of this work was to
show that the technique for constructing decision trees from examples is fairly
reliable. Commercial systems today are effective tools that have achieved notable
results. Advances have been made that will allow such systems to deal with noisy,
partial data that is typical of advanced real-world applications. Several centers are
working to increase the performance of the underlying algorithms.

Dawn Iacobucci, Maria Petrescu, Anjala Krishen, Michael Bendixen, 2019 The
state of marketing analytics in research and practice. This study examines the
usefulness of marketing analytics for marketing research and practice by conducting
a systematic assessment of marketing research in the developing new field of
"marketing analytics." They identified the important themes and concepts linked to
marketing analytics in marketing research, such as big data, marketing metrics, and
marketing analytics value, using a semantic and cluster analysis. This article adds
to the marketing literature by incorporating critical marketing analytics studies and
offering an overview of the research landscape. For a more natural manner to apply
theoretical discoveries in practice, practitioners receive recommendations and a
summary of the review. Academics can use these findings to discuss and show the
application and benefits of marketing analytics in the classroom.

Dr. Madhu Bala and Mr. Deepak Verma, 2018 A Critical Review of Digital
Marketing. Digital marketing, such as search engine optimization (SEO), search
engine marketing (SEM), content marketing, influencer marketing, content
automation, e-commerce marketing, campaign marketing, and social media
marketing, social media optimization, e–mail direct marketing, display advertising,
e–books, optical discs, and games, are becoming increasingly common in our
advancing technology, according to this study. Digital marketing is cost-effective and
has a significant commercial impact.

Kishan Prajapati, 2020 A Study on Digital Marketing and It’s Impacts. The research
focuses on digital marketing and its effects. The more time people spend online
each year, the more digital platforms they utilize play an increasingly important role
in their lives. Because customers may access digital platforms from anywhere in the
world at any time, businesses must shift their marketing strategies from traditional
to digital. It demonstrates that consumers prefer to shop online than go to a physical
store. As customer buying habits evolve, businesses must adapt their advertising
strategies and embrace digital marketing channels.

Dr. Tejas B. Vyas, 2021 A Study on Analysis of Digital Marketing. This research is
focused on digital marketing. Digital marketing is more than just placing
advertisements in entrances; it also includes integrated managements and
coordinated stations. Promoters are required to successfully use these segments in
order to arrive at objective meetings and create a product. In this computerized time,
the product promoter is no longer the concierge; instead, the supervisors are those
who are involved in the advanced phases. As a result, products must provide stages
for clients to comprehend their item or obtain a true texture of that product. He
accepts that this business story will be really valuable for marketers who want to
learn about electronic marketing and anticipate future systems.

Molly Maycock, Patrick Spenner, Robert Hamshar and Shelley West, 2012 The
Digital evolution in B2B Marketing Research Conducted by Marketing Leadership
Council Google. The goal of this study is to uncover common obstacles that
marketing professionals in major B2B firms have when it comes to building a digital
marketing competence and supporting a content-led marketing strategy. Create
frameworks based on proven procedures and expert analysis for understanding and
overcoming those difficulties. Provide actionable ideas and case studies to assist
B2B marketing executives in overcoming their issues.

Joel Järvinen, Aarne Tollinen, Heikki Karjaluoto and Chanaka Jayawardhena,

2012 Digital and Social Media Marketing Usage in B2b Industrial Section. The
study's goal was to look into B2B companies' digital marketing tools, goals,
measurement systems, and impediments to adoption. To answer the research
questions and satisfy the study objective, a thorough literature evaluation of B2B
digital marketing was undertaken. Five propositions were generated based on the
literature review to guide the analysis of study data. The theories were put to the
test in a study of B2B companies. The empirical evidence backs up the majority of
the claims.

Neeraj Pandey, Preeti Nayal and Abhijeet Singh Rathore, 2019 Digital marketing
for B2B organizations: structured literature review and future research directions.
The goal of this study was to achieve the research's goal, therefore many research
articles on B2B digital marketing usage were reviewed. Several developing themes
were discovered, and the majority of them were validated through semi structured
interviews with industry professionals. Finally, it can be concluded that academic
study in the field of B2B digital marketing is still in its infancy. Finally, because each
business has its own strategy to implementing B2B digital marketing, future studies
can adapt the framework to diverse industries such as manufacturing, information
technology, fast-moving consumer products, and healthcare.

Asaad Ali Karam and Serdar Saydam, 2015 An Analysis Study of Improving Brand
Awareness and Its Impact on Consumer Behaviour Via Media in North Cyprus (A
Case Study of Fast Food Restaurants). The findings of this study are in line with
those of prior investigations. This idea shows that the bulk of marketing
communications instruments used to expose a brand have inadvertent participation
methods. Customer loyalty appears to boost brand awareness during the
information rally process, according to this study. The gratification-and-use principle
According to theory, one of the results of customer behavior in the context of social
media is brand awareness. The most effective variable on brand awareness,
according to this study, is customer image since it maximizes awareness during the
engagement and contact stages. The study also shows the relationship between
media and brand awareness, as well as the Integrating Marketing Communications
Model for establishing brand equity.

Jose Prabhu. J, 2019 A Study of Digital Marketing and Digital Boom for Creating
Brand Awareness: The Importance and Suggestions for Creating a Successful
Start-up. Digital marketing has become an integral aspect of many businesses'
operations. Even for the entrepreneur these days, there is a very inexpensive and
effective way to market his or her products or services. Digital marketing may have
a better chance of succeeding if it prioritizes client demands. To choose the best
way to drive up advanced advertising execution, organizations should create
inventive client experiences and clear media methods.

Sya’idah. E. H, Sugiarti. N, Jauhari. T and Dewandaru. B, 2019 The

Implementation of Digital Marketing towards Brand Awareness. Based on the
foregoing, it can be concluded that the use of digital marketing can help the
Ayamjoper.id Company streamline its operations, particularly in terms of product
promotion and sales, despite its vast variety. Furthermore, using a digital marketing
plan using all media, including as YouTube, Facebook, Google My Business, and
notably the official company website, will help increase Ayamjoper.id's brand
awareness.

Anna Makrides, Demetris Vrontis and Michael Christofis, 2019 The Gold Rush
of Digital Marketing: Assessing Prospects of Building Brand Awareness Overseas.
This research produced some intriguing findings that corroborated current literature,
demonstrating that a SME can improve its exposure to a wider audience by taking
advantage of the myriad opportunities provided by the digital world. Given that there
is frequently a disparity between what customers want and what marketers actually
do to engage them, these insights can be extremely beneficial to both organizations
and marketers in narrowing the gap between consumer preferences and their
actions. Finally, there has been a lot of discussion in the marketing and consumer
research literature about digital marketing. Given the fast-paced nature of the digital
world, however, research that aims to increase our understanding of new
occurrences and establish theoretical frameworks in areas where there are none
will be the most helpful.

Krishnaprabha. S and Tarunika. R, 2020 An Analysis on building Brand

Awareness through Digital Marketing Initiatives. The correlation between the main
research variables shows that there is a positive and significant association between
digital marketing and brand awareness. The model is adequate and fits the obtained
data, according to the regression analysis. As a result of their use of digital
marketing, businesses can enhance consumer loyalty and communication with
them on a daily basis. When compared to the traditional marketing communication
methods that organizations use, consumers regard digital media as a more reliable
source of information.
Dwiana Rahmadiati Putri, 2021 Digital Marketing Strategy to Increase Brand
Awareness and Customer Purchase Intention. The study was based on Ailesh
Green Consulting's major concern, which is a lack of brand awareness and client
buy intent. Based on the questionnaire, the author offered four suggestions to Ailesh
Green Consulting to improve their brand awareness and client purchase intent.
Personal selling has not used digital marketing, and the existing digital marketing
plan is a website. Promotions are still reliant on word of mouth, and personal selling
has not used digital marketing.
 CHAPTER 3
RESEARCH METHODOLOGY

3.1 RESEARCH DESIGN

Descriptive research involves many types of surveys and fact-finding inquiries. The
primary goal of descriptive research is to describe the current state of
circumstances. The data collected through the research paper, theory paper and
finding the facts, which is Secondary Data.

Survey method allows you to gather large volumes of data that can be analyzed for
frequencies, averages and patterns. The data I have collected through circulating
my questionnaire link (google form), which is Primary Data.

3.2 SAMPLING TECHNIQUE

The sampling technique used here is Non-probability Sampling - Convenient

Sampling Method. The Sample size is 218 which is collected to the general public
Chennai city. The Period of study for my survey is Three months. The collection of
data for survey took 15 days for 218 responses. My targeted audience for this study
is Marketing and Business People.

3.3 SOURCES OF DATA

One of the most crucial elements of a research paper is data collection. The data
used in research approach must be correct and up to date. There are two different
types of data collection procedures.

➢ PRIMARY DATA
In this study, a questionnaire method was utilized to gather data, and it was
distributed in the form of a link.

➢ SECONDARY DATA
Secondary data refers to information that is already available, i.e. information that
has previously been gathered and processed by someone else. The study's
secondary data was gathered from books, company websites, publications, and
other sources.

3.4 STRUCTURE OF QUESTIONNAIRE

QUESTIONNAIRE PREPARATION
Any research project requires appropriate data, which can be obtained via a
timetable or questionnaire. It is simple to determine the level of involvement of so
many people in the city using a questionnaire.

PILOT SURVEY
It is critical to determine the instrument's applicability to the population being studied
before gathering relevant data to test the hypothesis. As a result, a pilot study was
conducted with the goal of evaluating the study's tools and determining whether they
are giving the information required.

TYPES OF QUESTIONS
➢ Direct questions
➢ Close ended questions
➢ Multiple choice questions
➢ Likert scaling questions
➢ Rank questions

3.5 SAMPLE SIZE

✓ Sample Size - 218

✓ Sample Location – Chennai

3.6 HYOTHESIS / ANALYTICAL TOOLS

HYPOTHESIS TESTING
➢ H0 – Null hypothesis (there is no significant relationship between the
variables).
 ➢ H1 – Alternative hypothesis (there is significant relationship between the
variables)

After analyzing the data, hypothesis testing is done. It will result in either accepting
or rejecting the hypothesis.

ANALYTICAL TESTS
➢ Chi-Square
➢ One Way Anova
➢ Rank Correlation

INFERENCE
After setting and testing the hypothesis, I came out with the conclusion. The
explanation of theory can also be considered as inference.

PREPATION OF REPORT AND PRESENTATION OF REPORT

Finally, I prepared a final report along with conclusion and suggestion, with the
inference and findings.
 CHAPTER 4
DATA ANALYSIS AND INTERPRETATION

4.1 TABLES AND CHARTS OF MY QUESTIONNAIRE

4.1.1 TABLE NO.1

Age wise classification of respondents
Age Frequency Percentage
21 – 30 years 100 45.90%
31 – 40 years 63 28.90%
41 – 50 years 30 13.80%
Above 50 years 25 11.50%
Total 218 100%
CHAT NO.1
Chart representing the age wise classification of respondents.

AGE
Above 50 years,
11.50%

41 – 50 years,
13.80% 21 – 30 years,
45.90%

31 – 40 years,
28.90%

SOURCE: Primary Data

INTERPRETATION:
From the above table and chart shows that 45.90% of respondents are from age
group between 21-30, 28.90% of respondents are from age group between 31-40,
13.80% of respondents are from age group between 41-50 and 11.50% of
respondents are from age group Above 50 years.

INFERENCE:
Majority (45.90%) of respondents are from age group between 21-30 years.
4.1.2 TABLE NO.2
Gender wise classification of respondents
Gender Frequency Percentage
Male 110 50.50%
Female 108 49.50%
Total 218 100%
CHAT NO.2
Chart representing the gender wise classification of respondents.

GENDER

Female, 49.50%

Male, 50.50%

SOURCE: Primary Data

INTERPRETATION:
From the above table and chart shows that 50.50% from Male category and 49.50%
from Female category in the gender wise respondents.
INFERENCE:
Majority (50.50%) of respondents are male category based on my data collections.
4.1.3 TABLE NO.3
Educational qualification wise classification of respondents.
Educational Frequency Percentage
Qualification
Professional degree 35 16.10%
Post-graduation 84 38.50%
Under-graduation 91 41.70%
Other 8 3.70%
Total 218 100%
CHART NO.3
This chart represents the Educational qualification wise classification of
respondents.

EDUCATIONAL QUALIFICATION
Other, 3.70% Professional
degree, 16.10%

Under-
graduation,
41.70%

Post-
graduation,
38.50%

SOURCE: Primary Data

INTERPRETATION:
From that above table and chart 16.10% of respondents are Professional degree
holder, 38.50% of respondents are Post-graduated, 41.70% of respondents are
Under-graduated and 3.70% of responded to others.
INFERENCE:
Majority (41.70%) of respondents are Under-graduated.
4.1.4 TABLE NO.4
Marital status wise classification of respondents.
Marital Status Frequency Percentage
Married 118 54.10%
Unmarried 100 45.90%
Total 218 100%
CHART NO.4
This chart represents the marital status wise classification of respondents.

MARITAL STATUS

Married,
54.10%

Unmarried,
45.90%

SOURCE: Primary Data

INTERPRETATION:
From the above table and chart 54.10% of respondents are Married and 45.90% of
respondents are Unmarried.

INFERENCE:
Majority (54.10%) of respondents are Married.
4.1.5 TABLE NO.5
Occupation wise classification of respondents.
Occupation Frequency Percentage
Business 89 40.80%
Employed 82 37.60%
Services 15 6.90%
Other 32 14.70%
Total 218 100%
CHART NO.5
This chart represents the Occupation wise classification of respondents.

OCCUPATION
Other, 14.70%

Services, 6.90%
Business,
40.80%

Employed,
37.60%

SOURCE: Primary Data

INTERPRETATION:
From that above table and chart 40.80% of respondents are Business, 37.60% of
respondents are Employed, 6.90% of respondents are Service and 14.70% of
respondents are Other.
INFERENCE:
Majority (40.80%) of respondents are Business people.
4.1.6 TABLE NO.6
Annual Income wise classification of respondents.
Annual income Frequency Percentage
Below Rs. 1,50,000 32 14.70%
Rs. 1,50,000 – Rs. 3,00,000 23 10.60%
Rs. 3,00,000 – Rs. 5,00,000 70 32.10%
Above Rs. 5,00,000 93 42.70%
Total 218 100%
CHART NO.6
This chart represents the Annual Income wise classification of respondents.

ANNUAL INCOME
Below Rs.
1,50,000,
14.70%

Rs. 1,50,000 –
Rs. 3,00,000,
10.60%

Above Rs.
5,00,000,
42.70% Rs. 3,00,000 –
Rs. 5,00,000,
32.10%

SOURCE: Primary Data

INTERPRETATION:
From that above table and chart 14.70% of respondents are Below Rs.1,50,000,
10.60% of respondents are between Rs.1,50,000-3,00,000, 32.10% of respondents
are between Rs.3,00,000-5,00,000 and 42.70% of respondents are Above
Rs.5,00,000.
INFERENCE:
Majority (42.70%) of respondents are earning Above Rs.5,00,000.
Variables related Questions:
4.1.7 TABLE NO.7
Question based on responses
Do you aware of Digital Marketing sources

Digital Marketing Frequency Percentage

sources
Yes 183 83.90%
No 5 2.30%
Maybe 30 13.80%
Total 218 100%
CHART NO.7
This chart representing the response for the above questions.

Digital Marketing sources

13.80%

2.30%

83.90%

Yes No Maybe

SOURCE: Primary Data

INTERPRETATION:
From the above table and chart 83.90% of respondents have mentioned as Yes,
2.30% of respondents have mentioned as No and 13.80% of respondents have
mentioned as Maybe.

INFERENCE:
Majority (83.90%) of respondents are aware about digital marketing sources.
4.1.8 TABLE NO.8
Question based on responses
From the following Digital Marketing sources, which source you have heard off
Digital Marketing sources Frequency Percentage
Predictive Analytics 125 57.30%
Social Media Marketing 116 53.20%
Content Marketing 76 34.90%
Marketing Analytics 68 31.20%
Average 218 100%
CHART NO.8
This chart representing the response for the above questions.

Digital Marketing sources

Marketing Analytics 31.20%

Content Marketing 34.90%

Social Media Marketing 53.20%

Predictive Analytics 57.30%

0.00% 10.00% 20.00% 30.00% 40.00% 50.00% 60.00% 70.00%

SOURCE: Primary Data

INTERPRETATION:
From the above table and chart 57.30% of respondents have mentioned Predictive
Analytics, 53.20% of respondents have mentioned Social Media Marketing, 34.90%
of respondents have mentioned Content Marketing and 31.20% of respondents
have mentioned Marketing Analytics.

INFERENCE:
Majority (57.90%) of respondents have heard off Predictive Analytics.
4.1.9 TABLE NO.9
Question based on responses
On a scale of 1 – 5 rate your preference on Predictive Analytics
Predictive Analytics Frequency Percentage
1 18 8.30%
2 27 12.40%
3 78 35.80%
4 45 20.60%
5 50 22.90%
Total 218 100%

CHART NO.9
This chart representing the response for the above questions.

PREDICTIVE ANALYTICS
35.80%

22.90%
20.60%
12.40%
8.30%

1 2 3 4 5

SOURCE: Primary Data

INTERPRETATION:
From the above table and chart 8.30% of respondents rated as 1, 12.40% of
respondents rated as 2, 35.80% of respondents rated as 3, 20.60% of respondents
rated as 4 and 22.90% of respondents rated as 5.
INFERENCE:
Majority (35.80%) of respondents have rated as 3 for Predictive Analytics.
4.1.10 TABLE NO.10
Question based on responses
Predictive analytics technique you prefer as a Marketer
Technique Frequency Percentage
Decision tree 115 52.80%
Test analysis 78 35.80%
Neural networks 25 11.50%
Total 218 100%
CHART NO.10
This chart representing the response for the above questions.

PREDICTIVE ANALYTICS TECHNIQUE

Neural
networks,
11.50%

Decision tree,
52.80%

Test analysis,
35.80%

SOURCE: Primary Data

INTERPRETATION:
From the above table and chart 52.80% of respondents prefer Decision tree, 35.80%
of respondents prefer Test analysis and 11.50% of respondents prefer Neural
networks.
INFERENCE:
Majority (52.80%) of respondents prefer Decision tree technique in predictive
analytics.
4.1.11 TABLE NO.11
Question based on responses
Predictive Analytics Model you are aware off
Model Frequency Percentage
Time series model 85 39%
Cluster model 73 33.50%
Classification model 38 17.40%
Forecast mode 22 10.10%
Total 218 100%
CHART NO.11
This chart representing the response for the above questions.

PREDICTIVE ANALYTICS MODEL

Forecast mode,
10.10%

Classification
model, 17.40%

Time series
model, 39%

Cluster model,
33.50%

SOURCE: Primary Data

INTERPRETATION:
From the above tables and charts 39% of respondents have mentioned Time series
model, 33.50% of respondents have mentioned Cluster model, 17.40% of
respondents have mentioned Classification model and 10.10% of respondents have
mentioned Forecast model.
INFERENCE:
Majority (39%) of respondents are aware about Time series model in predictive
analytics.
4.1.12 TABLE NO.12
Question based on responses
Could you specify the favorable Predictive Analytics tools as a marketer
Tools Frequency Percentage
Data mining 80 36.70%
Machine learning 101 46.30%
Unified marketing measurement 37 17%
Total 218 100%
CHART NO.12
This chart representing the response for the above questions.

PREDICTIVE ANALYTICS TOOLS

Unified
marketing
measurement,
17%

Data mining,
36.70%

Machine
learning,
46.30%

SOURCE: Primary Data

INTERPRETATION:
From the above table and chart 36.70% of respondents have mentioned Data
mining, 46.30% of respondents have mentioned Machine learning and 17% of
respondents have mentioned Unified marketing measurements.
INFERENCE:
Majority (36.70%) of respondents prefer Data mining as predictive analytics tools.
4.1.13 TABLE NO.13
Question based on responses
Problems can affect the Predictive Analytics
Problems Frequency Percentage
Lack of important data 45 20.60%
Lack of understanding 60 27.50%
to use data
Identifying the best tool 73 33.50%
Targeted advertisement 40 18.40%
Total 218 100%
CHART NO.13
This chart representing the response for the above questions.

PREDICTIVE ANALYTICS PROBLEMS

Targeted Lack of
advertisement, important data,
18.40% 20.60%

Lack of
Identifying the understanding
best tool, to use data,
33.50% 27.50%

SOURCE: Primary Data

INTERPRETATION:
From the above table and chart 20.60% of respondents have mentioned Lack of
important data, 27.50% of respondents have mentioned Lack of understanding to
use data, 33.50% of respondents have mentioned Identifying best tool and 18.40%
of respondents have mentioned Targeted advertisement.
INFERENCE:
Majority (33.50%) of respondents have mentioned Identifying best tool as predictive
analytics problem.
4.1.14 TABLE NO.14
Question based on responses
Predictive Analytics report is useful for decision making in the current organization /
project
Decision Making Frequency Percentage
Strongly disagree 8 3.70%
Disagree 12 5.50%
Neutral 67 30.70%
Agree 80 36.70%
Strongly agree 51 23.40%
Total 218 100%
CHART NO.14
This chart representing the response for the above questions.

DECISION MAKING
Strongly
disagree, 3.70%
Disagree,
5.50%
Strongly agree,
23.40%

Neutral,
30.70%

Agree, 36.70%

SOURCE: Primary Data

INTERPRETATION:
From the above table and chart 3.70% of respondents have mentioned Strongly
disagree, 5.50% of respondents have mentioned Disagree, 30.70% of respondents
have mentioned Neutral, 36.70% of respondents have mentioned Agree and
23.40% of respondents have mentioned Strongly agree.
INFERENCE:
Majority (36.70%) of respondents have agreed that predictive analytics report is
useful for decision making in the current organization / project.
4.1.15 TABLE NO.15
Question based on responses
Strategy you most prefer for Digital Marketing development as a marketer
Digital Marketing Frequency Percentage
Strategy
Influencer marketing 37 17%
Social media platforms 97 44.50%
E-Marketing 51 23.40%
Mobile Marketing 33 15.10%
Total 218 100%
CHART NO.15
This chart representing the response for the above questions.

DIGITAL MARKETING STRATEGY

Mobile
Influencer
Marketing,
marketing, 17%
15.10%

E-Marketing,
23.40%

Social media
platforms,
44.50%

SOURCE: Primary Data

INTERPRETATION:
From the above table and chart 17% of respondents have mentioned Influencer
marketing, 44.50% of respondents have mentioned Social media platforms, 23.40%
of respondents have mentioned E-Marketing and 15.10% of respondents have
mentioned Mobile marketing.
INFERENCE:
Majority (44.50%) of respondents have mentioned Influencer marketing strategy for
digital marketing development.
4.1.16 TABLE NO.16
Question based on responses
Digital Marketing tools most used by you in Business to Business
Digital Marketing Tools Frequency Percentage
Design tool 50 22.90%
Analytics tool 55 25.20%
Content marketing tool 72 33%
Display advertisement 41 18.80%
tool
Total 218 100%
CHART NO.16
This chart representing the response for the above questions.

DIGITAL MARKETING TOOLS

Display Design tool,
advertisement 22.90%
tool, 18.80%

Analytics tool,
25.20%
Content
marketing tool,
33%

SOURCE: Primary Data

INTERPRETATION:
From the above table and chart 22.90% of respondents have mentioned Design
tool, 25.20% of respondents have mentioned Analytics tool, 33% of respondents
have mentioned Content marketing tool and 18.80% of respondents have
mentioned Display advertisement tool.
INFERENCE:
Majority (33%) of respondents have mentioned Content marketing tool used in B2B.
4.1.17 TABLE NO.17
Question based on responses
As an assumption from marketer, Customer prefer digital marketing for
Customer’s Preference Frequency Percentage
Product development 42 19.30%
Easy purchase 81 37.20%
Convenient price 65 29.80%
Easy return/repay 30 13.80%
Total 218 100%

CHART NO.17
This chart representing the response for the above questions.

CUSTOMER’S PREFERENCE
Easy Product
return/repay, development,
13.80% 19.30%

Convenient
price, 29.80%
Easy purchase,
37.20%

SOURCE: Primary Data

INTERPRETATION:
From the above table and chart 19.30% of respondents have mentioned Product
development, 37.20% of respondents have mentioned Easy purchase, 29.80% of
respondents have mentioned Convenient price and 13.80% of respondents have
mentioned Easy return/repay.
INFERENCE:
Majority (37.20%) of respondents have mentioned customer prefer digital marketing
for Easy purchase.
4.1.18 TABLE NO.18
Question based on responses
Satisfaction level of customer towards digital marketing performance assuming as
marketer.
Customer’s Satisfaction Level Frequency Percentage
Very satisfied 65 29.80%
Satisfied 91 41.70%
Neutral 54 24.80%
Dissatisfied 6 2.80%
Very dissatisfied 2 0.90%
Total 218 100%

CHART NO.18
This chart representing the response for the above questions.

CUSTOMER’S SATISFACTION LEVEL

Very dissatisfied,
Dissatisfied,
0.90%
2.80%

Very satisfied,
29.80%

Neutral,
24.80%

Satisfied,
41.70%

SOURCE: Primary Data

INTERPRETATION:
From the above table and chart 29.80% of respondents have mentioned Very
satisfied, 41.70% of respondents have mentioned Satisfied, 24.80% of respondents
have Neutral, 2.80% of respondents have mentioned Dissatisfied and 0.90% of
respondents have mentioned Very dissatisfied.
INFERENCE:
Majority (41.70%) of respondents are Satisfied with digital marketing performance.
4.1.19 TABLE NO.19
Question based on responses
Rate on a scale of 1- 5 on Customer satisfaction towards digital marketing from
Marketer’s perception
Customer satisfaction 1 2 3 4 5
Price 6.90% 11.50% 28% 17.90% 35.80%
Product 3.70% 14.20% 39.50% 22% 20.60%
Delivery 6.40% 11.50% 28.90% 34.40% 18.80%
Shopping experience 11.50% 12.40% 22.90% 30.70% 22.50%
Customer service 9.60% 11.50% 30.30% 20.60% 28%
CHART NO.19
This chart representing the response for the above questions.

CUSTOMER SATISFACTION
1 2 3 4 5
39.50%
35.80%

34.40%

30.70%

30.30%
28.90%
28%

28%
22.90%

22.50%
20.60%

20.60%
18.80%
22%
17.90%

14.20%

12.40%
11.50%

11.50%

11.50%

11.50%
9.60%
6.90%

6.40%
3.70%

PRICE PRODUCT DELIVERY SHOPPING CUSTOMER

EXPERIENCE SERVICE

SOURCE: Primary Data

INTERPRETATION:
From the above table and chart the 218 respondents have mentioned towards
customer satisfaction.
➢ Price, 6.90% of respondents have rated for 1, 11.50% of respondents have
rated for 2, 28% of respondents have rated for 3, 17.90% of respondents
have rated for 4 and 35.80% of respondents have rated for 5.
➢ Product, 3.70% of respondents have rated for 1, 14.20% of respondents have
rated for 2, 39.50% of respondents have rated for 3, 22% of respondents
have rated for 4 and 20.60% of respondents have rated for 5.
 ➢ Delivery, 6.40% of respondents have rated for 1, 11.50% of respondents
have rated for 2, 28.90% of respondents have rated for 3, 34.40% of
respondents have rated for 4 and 18.80% of respondents have rated for 5.
➢ Shopping experience, 11.50% of respondents have rated for 1, 12.40% of
respondents have rated for 2, 22.90% of respondents have rated for 3,
30.70% of respondents have rated for 4 and 22.50% of respondents have
rated for 5.
➢ Customer service, 9.60% of respondents have rated for 1, 11.50% of
respondents have rated for 2, 30.30% of respondents have rated for 3,
20.60% of respondents have rated for 4 and 28% of respondents have rated
for 5.
INFERENCE:
➢ Majority (35.80%) of respondents have rated 5 for Price as customer
satisfaction.
➢ Majority (39.50%) of respondents have rated 3 for Product as customer
satisfaction.
➢ Majority (34.40%) of respondents have rated 4 for Delivery as customer
satisfaction.
➢ Majority (30.70%) of respondents have rated 4 for Shopping experience as
customer satisfaction.
➢ Majority (30.30%) of respondents have rated 3 for Customer service as
customer satisfaction.
4.1.20 TABLE NO.20
Question based on responses
Digital marketing fraud you have identified the most as a marketer

Digital Marketing Fraud Frequency Percentage

Domain spoofing 52 23.90%
Click injection 46 21.10%
Cookie stuffing 90 41.30%
Ad stacking 30 13.80%
Total 218 100%
CHART NO.20
This chart representing the response for the above questions.

DIGITAL MARKETING FRAUD

Ad stacking, Domain
13.80% spoofing,
23.90%

Cookie stuffing, Click injection,

41.30% 21.10%

SOURCE: Primary Data

INTERPRETATION:
From the above table and chart 23.90% of respondents have mentioned Domain
spoofing, 21.10% of respondents have mentioned Click injection, 41.30% of
respondents have mentioned Cookie stuffing and 13.80% of respondents have
mentioned Ad stacking.

INFERENCE:
Majority (41.30%) of respondents have mentioned Cookie stuffing fraud identified
as a marketer.
4.1.21 TABLE NO.21
Question based on responses
Impact on the business due to digital fraud

Digital Fraud Impact Frequency Percentage

Wasting advertising budget 42 19.30%
Harming brand’s reputation 83 38.10%
Recovering money from fraudsters 61 28%
Generating fake leads 32 14.70%
Total 218 100%

CHART NO.21
This chart representing the response for the above questions.

DIGITAL FRAUD IMPACTWasting

Generating
fake leads, advertising
14.70% budget, 19.30%

Recovering
money from
fraudsters, 28% Harming
brand’s
reputation,
38.10%

SOURCE: Primary Data

INTERPRETATION:
From the above table and chart 19.30% of respondents have mentioned Wasting
advertising budget, 38.10% of respondents have mentioned Harming brand’s
reputation, 28% of respondents have mentioned Recovering money from fraudsters
and 14.70% of respondents have mentioned Generating fake leads.
INFERENCE:
Majority (38.10%) of respondents have mentioned Harming brand’s reputation as
digital fraud impact.
4.1.22 TABLE NO.22
Question based on responses
Could you specify the most favorable way to prevent digital marketing fraud
Digital Fraud Prevention Frequency Percentage
Maintain a add text file 31 14.20%
Setup custom alerts 80 36.70%
Feedback about page and 67 30.70%
add experience
Keep eye on copyright theft 40 18.30%
Total 218 100%
CHART NO.22
This chart representing the response for the above questions.

DIGITAL FRAUD PREVENTION

Maintain a add
Keep eye on text file,
copyright theft, 14.20%
18.30%

Feedback
about page and Setup custom
add alerts, 36.70%
experience,
30.70%

SOURCE: Primary Data

INTERPRETATION:
From the above table and chart 14.20% of respondents have mentioned Maintain a
add text file, 36.70% of respondents have mentioned Setup custom alerts, 30.70%
of respondents have mentioned Feedback about page and experience and 18.30%
of respondents have mentioned Keep eye on copyright theft.
INFERENCE:
Majority (36.70%) of respondents have mentioned Setup custom alerts way to
prevent digital frauds.
4.1.23 TABLE NO.23
Question based on responses
As a digital marketer, why do you prefer Predictive analytics
Why Predictive Analytics Frequency Percentage
Determining customer response 48 22%
Grow profitable customer 70 32.10%
Forecasting inventory resources 59 27.10%
Promoting cross-sell opportunity 41 18.80%
Total 218 100%
CHART NO.23
This chart representing the response for the above questions.

Promoting WHY PREDICTIVE ANALYTICS

cross-sell Determining
opportunity, customer
18.80% response, 22%

Forecasting
inventory Grow
resources, profitable
27.10% customer,
32.10%

SOURCE: Primary Data

INTERPRETATION:
From the above table and chart 22% of respondents have mentioned Determining
customer response, 32.10% of respondents have mentioned Grow profitable
customer, 27.10% of respondents have mentioned Forecasting inventory resources
and 18.80% of respondents have mentioned Promoting cross-sell opportunity.
INFERENCE:
Majority (32.10%) of respondents have mentioned Grow profitable customer for
preferring Predictive analytics.
4.1.24 TABLE NO.24
Question based on responses
As a marketer will you suggest predictive analytics to your friends and family
Will You Suggest Frequency Percentage
Yes 107 49.10%
No 76 34.90%
Maybe 35 16.10%
Total 218 100%
CHART NO.24
This chart representing the response for the above questions.

Will You Suggest

16.10%

49.10%

34.90%

Maybe No Yes

SOURCE: Primary Data

INTERPRETATION:
From the above table and chart 49.10% of respondents have mentioned Yes,
34.90% of respondents have mentioned No and 16.10% of respondents have
mentioned Maybe.
INFERENCE:
Majority (49.10%) of respondents have mentioned they will suggest predictive
analytics to their friends and family.
 4.2 TESTING

4.2.1 CHI SQUARE TEST

H0 – Null hypothesis there is no association relationship between the Preference on

Predictive Analytics and Predictive Analytics Model.
H1 – Alternative hypothesis there is association relationship between the Preference
on Predictive Analytics and Predictive Analytics Model.

PREFERENCE ON PREDICTIVE ANALYSIS * PREDICTIVE ANALYTICS MODEL

Crosstabulation

PREDICTIVE ANALYTICS MODEL

Time
Cluster Classification Forecast Total
series
model model model
model
Count 8 5 4 1 18
1 Expected
7.0 6.0 3.1 1.8 18.0
Count
Count 10 10 4 3 27
2 Expected
10.5 9.0 4.7 2.7 27.0
Count
PREFERENCE
Count 36 24 11 7 78
ON
3 Expected
PREDICTIVE 30.4 26.1 13.6 7.9 78.0
Count
ANALYSIS
Count 8 19 10 8 45
4 Expected
17.5 15.1 7.8 4.5 45.0
Count
Count 23 15 9 3 50
5 Expected
19.5 16.7 8.7 5.0 50.0
Count
Count 85 73 38 22 218
Total Expected
85.0 73.0 38.0 22.0 218.0
Count
 Chi-Square Tests

Asymptotic
Value Df Significance
(2-sided)
Pearson Chi-
14.065a 12 0.297
Square
Likelihood
14.939 12 0.245
Ratio
Linear-by-
Linear 0.167 1 0.683
Association
N of Valid
218
Cases

INTERPRETATION
Since 0.297 is greater than 0.05 at 5% level of significance, we should accept the
Null hypothesis and reject Alternate hypothesis. Hence, there is no association
relationship between the Preference on Predictive Analytics and Predictive
Analytics Model.
 4.2.2 ONE WAY ANOVA TEST

H0 – Null hypothesis there is no significant difference between the Occupation and

the Predictive Analytics Technique.
H1 – Alternative hypothesis there is significant difference between the Occupation
and the Predictive Analytics Technique.

Descriptives

OCCUPATION
95%
Confidence
Std. Std. Interval for
N Mean Minimum Maximum
Deviation Error Mean
Lower Upper
Bound Bound
Decision
115 2.035 1.108 0.103 1.830 2.239 1.00 4.00
Tree
Test
78 1.910 0.956 0.108 1.695 2.126 1.00 4.00
analysis

Neural
25 1.720 0.891 0.178 1.352 2.088 1.00 4.00
networks
Total 218 1.954 1.033 0.070 1.816 2.092 1.00 4.00

ANOVA
OCCUPATION
Sum of Mean
Df F Sig.
Squares Square

Between
2.269 2 1.134 1.064 0.347
Groups
Within
229.273 215 1.066
Groups
Total 231.541 217

INTERPRETATION
Since 0.347 is greater than 0.05 at 5% level of significance, we should accept the
Null hypothesis and reject Alternate hypothesis. Hence, there is no significant
difference between the Occupation and the Predictive Analytics Technique.
 4.2.3 RANK CORRELATIONS

Rank Correlations

Shopping Customer
Price Product Delivery
experience service
Pearson
1 .546** .586** .370** .343**
Correlation
Price Sig. (2-
0.000 0.000 0.000 0.000
tailed)
N 218 218 218 218 218
Pearson
.546** 1 .499** .408** .272**
Correlation
Product Sig. (2-
0.000 0.000 0.000 0.000
tailed)
N 218 218 218 218 218
Pearson
.586** .499** 1 .297** .406**
Correlation
Delivery Sig. (2-
0.000 0.000 0.000 0.000
tailed)
N 218 218 218 218 218
Pearson
.370** .408** .297** 1 .341**
Correlation
Shopping Sig. (2-
experience 0.000 0.000 0.000 0.000
tailed)
N 218 218 218 218 218
Pearson
.343** .272** .406** .341** 1
Correlation
Customer Sig. (2-
service 0.000 0.000 0.000 0.000
tailed)
N 218 218 218 218 218

INTERPRETATION
Since the rank correlation coefficient between second judge and third judge is
positive and highest 0.406 among the five coefficients. Therefore, the Delivery and
the Shopping experience are nearer in the ranking on Customer Satisfaction level
on digital marketing.
 CHAPTER 5
SUMMARY OF FINDINGS, SUGGESTIONS & CONCLUSION

5.1 FINDINGS

➢ Majority (45.90%) of respondents are from age group between 21-30 years.
➢ Majority (50.50%) of respondents are male category based on my data
collections.
➢ Majority (41.70%) of respondents are Under-graduated.
Majority (54.10%) of respondents are Married.
➢ Majority (40.80%) of respondents are Business people.
Majority (42.70%) of respondents are earning Above Rs.5,00,000.
➢ Majority (83.90%) of respondents are aware about digital marketing sources.
➢ Majority (57.90%) of respondents have heard off Predictive Analytics.
➢ Majority (35.80%) of respondents have rated as 3 for Predictive Analytics.
➢ Majority (52.80%) of respondents prefer Decision tree technique in predictive
analytics.
➢ Majority (39%) of respondents are aware about Time series model in
predictive analytics.
➢ Majority (36.70%) of respondents prefer Data mining as predictive analytics
tools.
➢ Majority (33.50%) of respondents have mentioned Identifying best tool as
predictive analytics problem.
➢ Majority (36.70%) of respondents have agreed that predictive analytics report
is useful for decision making in the current organization / project.
➢ Majority (44.50%) of respondents have mentioned Influencer marketing
strategy for digital marketing development.
➢ Majority (33%) of respondents have mentioned Content marketing tool used
in B2B.
➢ Majority (37.20%) of respondents have mentioned customer prefer digital
marketing for Easy purchase.
➢ Majority (41.70%) of respondents are Satisfied with digital marketing
performance.
➢ Majority (35.80%) of respondents have rated 5 for Price as customer
satisfaction.
➢ Majority (39.50%) of respondents have rated 3 for Product as customer
satisfaction.
➢ Majority (34.40%) of respondents have rated 4 for Delivery as customer
satisfaction.
➢ Majority (30.70%) of respondents have rated 4 for Shopping experience as
customer satisfaction.
➢ Majority (30.30%) of respondents have rated 3 for Customer service as
customer satisfaction.
➢ Majority (41.30%) of respondents have mentioned Cookie stuffing fraud
identified as a marketer.
➢ Majority (38.10%) of respondents have mentioned Harming brand’s
reputation as digital fraud impact.
➢ Majority (36.70%) of respondents have mentioned Setup custom alerts way
to prevent digital frauds.
➢ Majority (32.10%) of respondents have mentioned Grow profitable customer
for
➢ preferring Predictive analytics.
➢ Majority (49.10%) of respondents have mentioned they will suggest
predictive analytics to their friends and family.
➢ (52.8%) have suggested for productive Predictive Analytics approach.
5.2 SUGGESTIONS

➢ Predictive Analytics is best source of digital marketing. The Business people

should be more aware off the tools and techniques of the predictive analytics,
where they can bring up a best decision for the organization/business using
the composed report. The productive predictive Analytics approach enable
to get early warning.
➢ Since fixing the issue in early stage is easy as well as less effort, in
encouraging for fail fast approach. Data mining is effective, more promotional
programs can be planned. There should be regular tool for forecasting
promotional advertising techniques for professional. Predictive analytics is
growing analysis which helping business development.
➢ The advancements in the science of artificial intelligence and machine
learning have altered the realm of computation by introducing intelligent
computation approaches and algorithms. In the realm of predictive analytics,
artificial neural networks ushered in a revolution. With advances in machine
learning and the development of deep learning techniques and models in
predictive analytics.
➢ Most marketers have yet to use collaborative filtering tactics, despite the fact
that practically all successful ecommerce businesses and streaming services
use it to locate relevant items and services. In practice, collaborative filtering
boils down to making content consumption, cross-sell, or upsell
recommendations based on prior behavior.
➢ As a result, digital marketing has proven to be one of the most effective
strategies for all businesses to promote themselves because it is easier and
less expensive than traditional marketing. Having a clear goal in mind will
assist the entire team in determining what they should be aiming for.
➢ The context of the forecast, the relevance and availability of past data, the
desired degree of accuracy, the time period to be predicted, the cost/benefit
of the forecast to the organization, and the time available for analysis are all
factors that influence technique selection. This is important since it pushes
the team to focus on what needs to be done if the targets aren't met or if
they're deviating from the current tasks.
➢ The Forecasting can assist you in dealing with challenges, but it will be more
effective if you grasp the fundamental concepts of forecasting, what it can
and cannot do at this time, and which tactics are best suited to your needs.
➢ Fundraisers can use predictive analytics to learn about the best tactics and
timing to maximize revenues. Predictive analytics provides sophisticated
insights that provide you a competitive advantage in any industry. Recruiters
can precisely target their outreach using the information provided in order to
achieve success at the lowest feasible cost.
➢ Predictive analytics is often utilized in sales systems such as Salesforce, but
it may also be used to existing clients in field service or call centers.
Salespeople can then use this data to make recommendations or even
change product placement based on store-specific schematics. We can also
predict client happiness for certain things to analyses that are likely to be in
high demand in the near future.
5.3 CONCLUSION

➢ The best source of digital marketing is Predictive Analytics. The predictive

analytics is most preferred and used by business marketers and business
people, but are not aware of the term. Predictive analysis gives you the clear
view of the report, it makes predictions about future outcomes using historical
data in conjunction with statistical modeling, data processing techniques, and
machine learning.
➢ It's helpful for recognizing risks and opportunities. It's a powerful tool for a
company's forecasting strategy, and it's well-informed and useful for digital
marketing. It is a group of technologies that are used to uncover hidden
information in data and predict the future. Indeed, competition is tough, and
each company must be prepared and have important predictive data with a
high level of precision on which to base its decisions.
➢ Predictions of future events are frequently made based on the existence or
possibility of data. Continuous and discontinuous changes can be dealt with
using predictive analytics. Any value's output or future can be anticipated
based on the input parameters. There's also the possibility of adding new
features to current models to help them perform better in the task.
➢ Predictive analytics was used to better assess the impact of seasonal trends
on overall sales, which helped them shorten their sales cycles. We use data
analytics and business insights to construct intelligent self-learning systems
that aid in understanding the target audience, discovering hidden hazards,
and grabbing new opportunities as part of our machine learning services.
➢ Using the appropriate tools and technology, we contribute to the vision of
anticipating market trends, buying patterns, and future changes that may
affect the business. Across many industries, predictive analytics is being
used to power a variety of revenue-focused initiatives.
➢ Effective predictive analytics approaches are becoming more widely
available, putting forecasting capability within reach of virtually every
company. The information you gather can also be utilized to improve future
product design or establish better operating practices.
➢ Predictive Analytics is more well-known among respondents than other
digital marketing sources. Decision tree techniques, time series models, and
machine learning tools are the most popular among business personnel.
➢ The most difficult difficulty a marketer faces is determining the appropriate
instrument for prediction in digital marketing. Content marketing is the ideal
instrument to employ on social media platforms to cover and catch the
customer in digital marketing.
➢ Customers are really pleased with the results of digital marketing. Cookie
stuffing is one of the most common frauds, and it has a significant influence
on the brand's reputation. As a marketer, we may prevent this by making
unique changes to the site page. The primary goal of predictive analytics is
to increase profitable customer growth.
 REFERENCE
WEBSITES

➢ https://www.clicdata.com/blog/common-marketing-analytics-challenges/
➢ https://www.digitaldoughnut.com/articles/2020/july-2020/the-importance-of-
predictive-analytics
➢ https://medium.com/swlh/modern-challenges-of-predictive-modelling-
74c273b290b6
➢ https://www.marketingevolution.com/knowledge-center/the-role-of-
predictive-analytics-in-data-driven-marketing
➢ https://seleritysas.com/blog/2019/12/12/types-of-predictive-analytics-
models-and-how-they-work/
➢ https://www.rapidinsight.com/blog/11-examples-of-predictive-analytics/
➢ https://www.sap.com/india/cmp/dg/in-sap-augmented-analytics/index.
➢ https://econsultancy.com/what-is-predictive-analytics-and-what-are-its-
main-uses-for-marketers
➢ https://www.xenonstack.com/insights/what-is-predictive-analytics
➢ https://www.wayup.com/guide/top-5-tools-for-digital-marketing/
➢ https://www.marketingevolution.com/marketing-essentials/what-is-a-digital-
marketing-platform-marketing-evolution
➢ https://www.getcloudapp.com/blog/customer-satisfaction-surveys/
➢ https://blockthrough.com/blog/7-common-types-of-ad-fraud-and-how-to-
prevent-them/
➢ https://www.anura.io/blog/7-types-of-digital-ad-fraud-how-much-they-cost-
you
➢ https://supermetrics.com/blog/predictive-analytics-in-marketing
➢ https://www.analyticssteps.com/blogs/predictive-analytics-techniques-and-
applications
➢ https://swaarm.com/blog/what-makes-a-good-performance-marketer/
➢ https://www.cio.com/article/219788/7-projects-primed-for-predictive-
analytics.html
➢ https://marutitech.com/predictive-analytics-use-cases/#The_Solution
➢ https://www.riverlogic.com/blog/
➢ https://hevodata.com/learn/prescriptive-analytics/
➢ https://www.sigmamagic.com/blogs/analytics-advantages-and-limitations/
➢ https://www.marketo.com/digital-marketing
➢ https://mailchimp.com/marketing-glossary/digital-marketing/
➢ https://developers.google.com/machine-learning/crash-course
➢ https://www.sas.com/en_in/insights/analytics/machine-learning.html
➢ https://iide.co/blog/5-tips-successful-digital-marketing-strategy/
➢ https://hbr.org/1971/07/how-to-choose-the-right-forecasting-technique
➢ https://www.digitopia.agency/blog/the-best-digital-marketing-resources
➢ https://improvado.io/blog/cluster-analysis-for-marketers-the-ultimate-guide
➢ https://assets.kpmg/content/dam/kpmg/dk/pdf/dk-2020/04/Nets-KPMG-
Fighting-Fraud-with-a-Model-of-Models-whitepaper-2020
➢ https://inform.tmforum.org/features-and-analysis/2017/02/digital-
transformation-means-fraud-transformation/
➢ https://medium.com/swlh/machine-learning-based-digital-fraud-detection-
bad492232eb6
➢ https://www.marketsandmarkets.com/Market-Reports/fraud-detection-
prevention-market-1312.html
➢ https://www.jigsawacademy.com/blogs/business-analytics/fraud-detection-
analytics/
➢ https://idea.caseware.com/blog/the-truth-behind-detecting-fraud-using-data-
analytics
➢ https://www.demandjump.com/blog/what-is-marketing-research
➢ https://www.oberlo.com/ecommerce-wiki/market-research
➢ https://www.hotjar.com/blog/market-research/
➢ https://predictiveresearchinc.com/
➢ https://www.qualtrics.com/au/experience-management/research/predictive-
analytics/?rid=ip&prevsite=en&newsite=au&geo=IN&geomatch=au
➢ https://www.sas.com/en_us/insights/analytics/predictive-analytics.html
➢ https://www.essays.se/about/sample+of+predictive+research/
ARTICLES

➢ https://www.researchgate.net/publication/326071541_A_survey_of_predicti
ve_analytics_using_big_data_with_data_mining January 2018
DOI:10.1504/IJBRA.2018.092697
➢ https://www.researchgate.net/publication/326435728_Predictive_Analytics_
A_Review_of_Trends_and_Techniques July 2018 International Journal of
Computer Applications 182(1):31-37 DOI:10.5120/ijca2018917434
➢ https://www.jstor.org/stable/23042796 Vol. 35, No. 3 (September 2011),
➢ https://www.researchgate.net/publication/271312087_Decision_Making_in_
Reference_to_Model_of_Marketing_Predictive_AnalyticsTheory_and_Practi
ce/link/587df73b08ae9275d4eb4382/download March 2014
DOI:10.7206/mba.ce.2084-3356.90
➢ https://www.researchgate.net/publication/335027590_The_state_of_marketi
ng_analytics_in_research_and_practice September 2019Journal of
Marketing Analytics 7(2) DOI:10.1057/s41270-019-00059-2
➢ https://www.gibs.edu.in/wp-content/uploads/2021/06/A-STUDY-ON-
ANALYSIS-OF-DIGITAL-MARKETING.pdf
➢ https://www.jamescannella.com/resources/artificial-intelligence-in-
marketing-thesis Spring 2018
➢ https://www.researchgate.net/publication/342976767_Machine_Learning_Al
gorithms_for_Predictive_Analytics_A_Review_and_New_Perspectives July
2020 DOI:10.37896/HTL26.06/1159
➢ https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3829621 Posted: 20
Apr 2021
➢ https://ieeexplore.ieee.org/document/9527487 Aug.2021
DOI: 10.1109/ICoICT52021.2021.9527487
➢ https://iopscience.iop.org/article/10.1088/1757-899X/392/6/062202/pdf
MTMCE IOP Publishing IOP Conf. Series: Materials Science and
Engineering 392 (2018) 062202 DOI:10.1088/1757-899X/392/6/062202
➢ https://www.researchgate.net/publication/331675364_Research_on_Data_
Mining_Technology_Based_on_Machine_Learning_Algorithm/link/5c87c9c
a299bf1e02e29b6f8/download CISAT 2018 IOP Conf. Series: Journal of
 Physics: Conf. Series 1168 (2019) 032132 IOP Publishing doi:10.1088/1742-
6596/1168/3/032132
➢ https://www.researchgate.net/publication/49616224_Data_mining_techniqu
es_and_applications/link/57a9affe08ae659d18249ecd/download December
2010 Vol. 1 No. 4 301-305
➢ https://storm.cis.fordham.edu/~gweiss/selected-papers/quinlan86.pdf
Machine Learning 1: 81-106, 1986 © 1986 Kluwer Academic Publishers,
Boston - Manufactured in The Netherlands
➢ https://www.researchgate.net/publication/345634018_A_Study_on_Digital_
Marketing_and_It's_Impacts/link/5fa987bba6fdcc06242044cc/download
November 2020 DOI:10.13140/RG.2.2.21143.80809
➢ https://www.researchgate.net/publication/328253026_A_Critical_Review_of
_Digital_Marketing/link/5bc720c292851cae21a8b701/download
International Journal of Management, IT & Engineering Vol. 8 Issue 10,
October 2018, ISSN: 2249-0558 Impact Factor: 7.119
➢ https://research.nitie.ac.in/pdf/publisher-pdf-fulltext-digital-marketing-for-
b2b-organizations Emerald Publishing Limited [ISSN 0885-8624] [DOI
10.1108/JBIM-06-2019-0283]
➢ https://www.researchgate.net/publication/281117621_Digital_and_social_m
edia_marketing_usage_in_B2B_industrial_section/link/57396e9b08aea45e
e83ed3c9/download January 2012 The Marketing Management Journal
Volume 22, Issue 2, Pages 102-117
➢ https://www.thinkwithgoogle.com/_qs/documents/677/the-digital-evolution-
in-b2b-marketing_research-studies.pdf 2012 The Corporate Executive Board
Company. MLC3413412SYN
➢ https://ijbssnet.com/journals/Vol_6_No_1_Januaryr_2015/8.pdf
➢ https://www.ejbmr.org/index.php/ejbmr/article/download/1063/572European
Journal of Business and Management Research
Published: September12,2021 DOI:10.24018/ejbmr.2021.6.5.1063
➢ https://journals.resaim.com/ijresm/article/download/74/64
International Journal of Research in Engineering, Science and Management
Volume-3, Issue-7, July-2020 ISSN (Online): 2581-5792
➢ http://ijariie.com/AdminUploadPdf/A_Study_of_Digital_Marketing_and_Digit
al_Boom_for_Creating_Brand_Awareness__The_Importance_and_Suggest
 ions_for_Creating_a_Successful_Startup_ijariie9995.pdf Vol-5 Issue-2 2019
IJARIIE-ISSN(O)-2395-4396
➢ https://www.atlantis-press.com/article/125926951.pdf (ICSS 2019) volume
383
➢ https://www.researchgate.net/publication/335094470_The_Gold_Rush_of_
Digital_Marketing_Assessing_Prospects_of_Building_Brand_Awareness_O
verseas/link/602e4d08299bf1cc26d2b724/download Article in Business
Perspectives and Research · August 2019
DOI: 10.1177/2278533719860016
➢ https://cdn2.hubspot.net/hubfs/1878504/Marketing-Evolution-Forrester-The-
Current-State-Of-Marketing_Measurement-And-Optimization.pdf September
2018
➢ https://www.researchgate.net/publication/247831240_Marketing_performan
ce_measurement_which_way_is_up/link/53f994e60cf2e3cbf560428e/downl
oad January 2000 International Journal of Business Performance
Management 2(1)
DOI:10.1504/IJBPM.2000.000065
➢ https://www.researchgate.net/publication/257799016_Analysis_of_various_t
esting_techniques/link/568a654208ae051f9afa4922/download September
2014International Journal of Systems Assurance Engineering and
Management 5(3)
DOI:10.1007/s13198-013-0157-6
➢ https://www.researchgate.net/publication/225565312_Assessing_the_qualit
y_of_classification_models_Performance_measures_and_evaluation_proce
dures une 2011Open Engineering 1(2):132-158
DOI:10.2478/s13531-011-0022-9
➢ http://www.jait.us/uploadfile/2014/1223/20141223050800532.pdf2010
ACADEMY PUBLISHER
 APPENDIX
Study on Impact of Predictive Analytics for Marketer’s Engaging Performance After
the Pandemic
QUESTIONNAIRE

Basic Questions

1. Name of the respondents ___________.

2. Age of the respondents
a) 21 – 30 years
b) 31 – 40 years
c) 41 – 50 years
d) Above 50 years
3. Gender of the respondents
a) Male
b) Female
4. Educational qualification of the respondents
a) Professional degree
b) Post-graduation
c) Under-graduation
d) Other
5. Marital Status of the respondents
a) Married
b) Unmarried
6. Occupation of the respondents
a) Business
b) Employed
c) Services
d) Other
7. Annual income of the respondents
a) Below Rs. 1,50,000
b) Rs. 1,50,000 – Rs. 3,00,000
c) Rs. 3,00,000 – Rs. 5,00,000
d) Above Rs. 5,00,000
Variables related Questions:

8. Do you aware of Digital Marketing sources

a) Yes
b) No
c) Maybe
9. From the following Digital Marketing sources, which source you have heard
off
a) Predictive Analytics
b) Social Media Marketing
c) Content Marketing
d) Marketing Analytics
10. On a scale of 1 – 5 rate your preference on Predictive Analytics
11. Predictive analytics technique you prefer as a Marketer
a) Decision tree
b) Test analysis
c) Neural networks
12. Predictive Analytics Model you are aware off
a) Time series model
b) Cluster model
c) Classification model
d) Forecast model
13. Could you specify the favorable Predictive Analytics tools as a marketer
a) Data mining
b) Machine learning
c) Unified marketing measurement
14. Problems can affect the Predictive Analytics
a) Lack of important data
b) Lack of understanding to use data
c) Identifying the best tool
d) Targeted advertisement
15. Predictive Analytics report is useful for decision making in the current
organization / project
a) Strongly agree
 b) Agree
c) Somewhat
d) Disagree
e) Strongly disagree
16. Strategy you most prefer for Digital Marketing development as a marketer
a) Influencer marketing
b) Social media platforms
c) E-Marketing
d) Mobile Marketing
17. Digital Marketing tools most used by you in Business to Business
a) Design tool
b) Analytics tool
c) Content marketing tool
d) Display advertisement tool
18. As an assumption from marketer, Customer prefer digital marketing for
a) Product development
b) Easy purchase
c) Convenient price
d) Easy return/repay
19. Satisfaction level of customer towards digital marketing performance
assuming as marketer
a) Highly satisfied
b) Satisfied
c) Neutral
d) Dissatisfied
e) Highly dissatisfied
20. Rate on a scale of 1- 5 on Customer satisfaction towards digital marketing
from Marketer’s perception
a) Price
b) Product
c) Delivery
d) Shopping experience
e) Customer service
21. Digital marketing fraud you have identified most as a marketer
 a) Domain spoofing
b) Click injection
c) Cookie stuffing
d) Ad stacking
22. Impact on the business due to digital fraud
a) Wasting advertising budget
b) Harming brand’s reputation
c) Recovering money from fraudsters
d) Generating fake leads
23. Could you specify the most favorable way to prevent digital marketing fraud
a) Maintain a add text file
b) Setup custom alerts
c) Feedback about page and add experience
d) Keep eye on copyright theft
24. As a digital marketer, why do you prefer Predictive analytics
a) Determining customer response
b) Grow profitable customer
c) Forecasting inventory resources
d) Promoting cross-sell opportunity
25. As a marketer will you suggest predictive analytics to your friends and
family
a) Yes
b) No
c) Maybe
26. Do you have any other suggestions for productive Predictive Analytics
approach