Business Analytics

Megharaja B
Assistant Professor of Commerce
VSK University, Ballari
Introduction to Business Analytics
 Meaning
 Definition
 Characteristics
 Applications
 Classification or types
 Importance
 Tools and techniques
 Functions
 Reports
 Data scientist roles and Responsibility
 Overview of Machine learning, Business Intelligence & Data visualisation
What is Business Analytics?

 Business Analytics is the discovery and communication of

meaningful patterns of data and that to business‐related
problems
 It is the scientific process of transforming data

into insight for making better decisions

(INFORMS).
[data => information => knowledge =>
wisdom]
Business analytics is the process by which
businesses use statistical methods and
technologies for analysing historical data in
order to gain new insight and improve strategic
decision making.
Business analytics is measuring the
performance to make improvement to the
bottom line of the business.
What is BA?
BA is the use of:
data,
information technology,
statistical analysis,
quantitative methods, and
mathematical or computer‐based models
to help managers to gain improved insight about their business
operations and make better, fact‐based decisions.
Definitions
 BA is the extensive use of data, statistical and quantitative
analysis, explanatory and predictive models, and fact ‐based
management to drive decisions and actions (Davenport and
Harris).
As per a popular definition from authors
 Michael J Beller and Alan Barnett, “Business analytics refers to
the skills, technologies, and practices for continuous iterative
exploration and investigation of past business performance to
gain insight and drive business planning”
Characteristics of BA
Business analytics is the process of transforming data into insights
to improve business decisions.
 Data management,
 data mining,
 data visualization,
 predictive modeling,
 forecasting simulation, and
 optimization are some of the tools used to create insights from

data.
Business Analytics Applications
 Pricing decisions
 Financial and marketing activities
 Supply chain management
 Management of customer relationships
 Human resource planning
 Enterprise resource planning
 Production and inventory management
 Customers Relationship Management
Types/Classification of BA
 Descriptive analytics: studying historic data and drawing

inferences, summarising data into a few key matrices; What

has happened in the past?
 Diagnostic analytics: How and why of past business
performance take learning from this historic data to correct
course, root cause analyses. Why did it happen?
 Predictive analytics: historic data, statistical models, and

machine learning-> most probabilistic future performance

in same business ecosystem. What is likely to happen?
 Prescriptive analytics: ability to suggest the optimal

solution, a recommendation system, optimizing the

chances of a beneficial outcomes. What to do?
Types/Classification of BA
 Descriptive analytics: which tell us what has already happened;
 Diagnostic analytics: How and why of past performance for learning and

identify the root cause.

 Predictive analytics: Which show us what could happen
 Prescriptive analytics: which inform us what should happen in the future
Importance of Business Analytics
 There is a strong relationship of BA with: ‐
◦ profitability of businesses ‐
revenue of businesses ‐

shareholder return
 BA is a methodology or tool to make commercial decision.
 Operational efficiency: Primary and secondary
 Competitive advantage: utilise information, available data + various well thought
models= improve the business decision
 Converts available data into valuable information- required format presentation,
comfortable to the decision maker.
 BA enhances understanding of data
 BA is vital for businesses to remain competitive
 BA enables creation of informative report
 Tools & Techniques of Analytics
 Statistical Analysis : Statistical Analysis is the study of the collection, organization, analysis,
interpretation and presentation of data.
 Data Mining : Data Mining is the computational process of discovering patterns, trends and
behaviors, in large data sets using artificial intelligence, machine learning, statistics, and
database systems.
 Quantitative Analytics :The data analysis in statistics are generally divided into descriptive
statistics, exploratory data analysis (EDA), and confirmatory data analysis (CDA).
 Qualitative Data Analysis : Qualitative Data Analysis provides tools to assist with qualitative
research such as transcription analysis, coding and text interpretation, recursive abstraction,
content analysis, discourse analysis, and grounded theory methodology.
 Business Intelligence : Solution transforms the raw data into meaningful and useful
information for intuitive presentation of knowledge and for the publication of business
intelligence objects.
 Predictive Analytics : Predictive analytics is the branch of the advanced analytics which is
used to make predictions about unknown future events.
 Text Analytics : Text Analytics is the process of converting unstructured text data into
meaningful data for analysis, to measure customer opinions, product reviews, feedback, to
provide search facility, sentimental analysis and entity modeling to support fact based decision
making.
Functions of Analytics
 Research and Data Analysis
 Trouble Shooting and Problem-Solving
 Data visualisation
 Communicating Corrective Plans
 Meeting all Contract Requirements
 Others:

◦ Extract Requirements
◦ Analyze Information
◦ Communicate and Document the Findings
Reports in Analytics
 An analytical report a type of business report that helps you evaluate your
business decisions based on data insights.
 What makes an analytical report different is that it gives you recommendations
instead of just plain numbers.
 Analytical reports are based on historical data, and statistics and
provide predictive analysis for a specific issue, such as the conversion rate for
new products.
 Regardless of the method you choose, your analytical report should include the
following:
 A title page – including the main topic or purpose and the type of report
 Table of contents – in a logical or chronological order
 A Methods – specifying and presenting the methods used for the activity
 The main discussion – broken down into organized sections, including the heading,

the sub-heading, and the discussion's body.

 The conclusions – according to the results and information gathered in the business

report
 The recommendations – given by the employee who created the report
 Sections for bibliography or appendices – when necessary

To write a successful analytical report, make sure you follow these instructions:
 Identify the Problem
 Explain Your Methods
 Analyze Data
 Make Recommendations
Data Scientist Roles and Responsibility in business analytics
 Data analysis and exploration
 Machine learning and statistical modelling
 Feature engineering
 Data visualization
 Predictive modelling and forecasting
 Experimental design and testing
Data Scientist Roles and Responsibility
 Management
 Analytics
 Strategy/Design
 Collaboration
 Knowledge
 Other Duties
Business Analysis Vs Business Analytics
 The primary focus is on techniques  The primary focus is on data and
and functionalities. statistical analysis.
 Used to solve the problems that  Used to predict the future and plan

exist in the business and bring growth strategies.

positive change.  The tasks under this domain get
 The tasks under this domain are handled by the data analysts.
handled by business analysts.  The areas that are covered under
 The areas covered under business business analytics are business
analysis are business, enterprise, decisions, big data, and future
and process. strategy planning.

Business Analysis Business Analytics

An overview of Machine Learning
 Machine learning (ML) is a branch of artificial
intelligence (AI) that enables computers to “self-learn”
from training data and improve over time, without being
explicitly programmed.
 Machine learning algorithms are able to detect patterns in
data and learn from them, in order to make their own
predictions.
Machine Learning (ML)
 ML is a branch of artificial intelligence:
◦ Uses computing based systems to make sense out of data
 Extracting patterns, fitting data to functions, classifying data, etc
◦ ML systems can learn and improve
 With historical data, time and experience
◦ Bridges theoretical computer science and real noise data.

32
ML in real-life

33
Supervised and Unsupervised
Learning
 Unsupervised Learning
◦ There are not predefined and known set of outcomes
◦ Look for hidden patterns and relations in the data
◦ A typical example: Clustering

34
Supervised and Unsupervised
Learning
 Supervised Learning
◦ For every example in the data there is always a predefined
outcome
◦ Models the relations between a set of descriptive features
and a target (Fits data to a function)
◦ 2 groups of problems:
 Classification
 Regression

35
Supervised Learning
 Classification
◦ Predicts which class a given sample of data (sample of
descriptive features) is part of (discrete value).

 Regression
◦ Predicts continuous values.

36
 Machine Learning as a Process
- Define measurable and quantifiable goals
Define - Use this stage to learn about the problem

Objectives
- Normalization

Model Data -
Transformation

Deployment Preparation - Missing Values

- Outliers

- Study models accuracy

- Work better than the
naïve - Data Splitting

Model Model
approach or previous - Features Engineering
system - Estimating

Evaluation Building
- Do the results make sense Performance
in the context of the - Evaluation and Model
problem Selection

37
ML as a Process: Data Preparation
• Needed for several reasons
• Some Models have strict data requirements
• Scale of the data, data point intervals, etc
• Some characteristics of the data may impact dramatically on
the model performance
• Time on data preparation should not be underestimated

38
ML as a Process: Feature engineering
• Determine the predictors (features) to be used is one of the most
critical questions
• Some times we need to add predictors
• Reduce Number:
• Fewer predictors more interpretable model and less costly
• Most of the models are affected by high dimensionality, specially for non-
informative predictors
Wrappers Multiple models adding and removing
parameter
Algorithms that use models as input
and performance as output
Genetics Algorithms

Filters Evaluate the relevance of the predictor Based normally on correlations

• Binning predictors
ML as a Process: Model Building
 Data Splitting
◦ Allocate data to different tasks
 model training
 performance evaluation
◦ Define Training, Validation and Test sets
 Feature Selection (Review the decision made previously)
 Estimating Performance

◦ Visualization of results – discovery interesting areas of the problem

space
◦ Statistics and performance measures
 Evaluation and Model selection
◦ The ‘no free lunch’ theorem no a priory assumptions can be made
◦ Avoid use of favorite models if NEEDED

40
 Business Intelligence
Business Intelligence (BI) refers to the use of
strategies and tools that serve to transform
information into knowledge, in order to
improve the decision-making process in a
company.
An overview of Data Visualization
 Data visualization is defined as a graphical
representation that contains the information and
the data.
 By using visual elements like charts, graphs,

and maps, data visualization techniques provide an

accessible way to see and understand trends,
outliers, and patterns in data.
Data Visualisation
◦ Data- Information
◦ Visualisation-Pictorial/Graphical representation
 Decision making
 Finding solutions to problems
 For understanding the data clearly
 To find relationship among the data
 Comparative analysis
Data visualization can be used for:
 Making data engaging and easily digestible
 Identifying trends and outliers within a set of data
 Telling a story found within the data
 Reinforcing an argument or opinion
 Highlighting the important parts of a set of data