An AI Based Chat Bot For

Banking Applications using Intelligent Chat Bots

Ajmeera Kira
2023 International Conference on Research Methodologies in Knowledge Management, Artificial Intelligence and Telecommunication Engineering (RMKMATE) | 979-8-3503-0570-8/23/$31.00 ©2023 IEEE | DOI: 10.1109/RMKMATE59243.2023.10369062

Veda Vidhya
Department of Computer Science and
Assistant Professor
Engineering
Department of Computer Science and Engineering
MLR Institute of Technology
MLR Institute of Technology, Hyderabad
Hyderabad, India
[email protected]
[email protected]

DBK Kamesh Ms. Srilakshmi V

Professor Assistant Professor
Department of CSE, Malla Reddy Department of CSE(AI & ML)
Engineering College for Women, B V Raju Institute of Technology
maisammaguda, hyderabad-500100 [email protected]
[email protected]

D PAULRAJ
Professor,
Department of Computer Science and
Engineering,
R.M.K. Engineering College, Tamil
Nadu, India
[email protected]

dialogues more productive. A major expansion in the number of

ABSTRACT:
cloud-based chatbot services that are currently available for use in the
A chat and voice assistant that is powered by AI and is integrated production and development of chatbots has taken place in recent
into a banking application. This assistant translates data in such months. Famous examples include IBM Watson, Clever Bot, and the
a way that the text and audio are designed to simulate human ELIZA Chatbot [5]. These three are just a few of the many more. Due
conversations. Since their inception, voice and chat assistants to the fact that chatbots have become more sensitive over the course
have seen substantial technological advancement. The of the last few years, there has been a huge advancement in the art of
advancements that have been made in machine learning and interaction between people and machines during this time period.
natural language processing have made it possible for them to
A. CHATBOTS TYPES
now learn from their experiences and conduct conversations that
are more human-like. Because of their more human nature, they Prior to the beginning of the modern period, manual labour was an
are able to assist with a wide variety of tasks, such as calculating extremely important component in each and every aspect of the
loan interests, confirming facts regarding transactions, and
economy. [Before this epoch], technological development was not
checking savings.
nearly as advanced as it is today. One of the areas of business that has
I. INTRODUCTION reaped significant benefits from the creation of chatbots is customer
Both day-to-day life and commercial activities are profoundly altered service [6]. Nevertheless, not all chatbots can be placed neatly into a
by the introduction of new technologies. It is utilised by people all single category at the same time. When classifying chatbots, we take
over the world in a plethora of different methods and for a broad into account not only the usability of the user interface but also the
assortment of different reasons [1]. Over the past few years, there has algorithms that are used and the technology that is used below. The
been a rise in general curiosity regarding artificial intelligence. There
following are the three primary classifications of chatbots:
are several different approaches taken by artificial intelligence to
simulate human intelligence. Chatbots powered by artificial i. Keyword Recognition-Based Chatbots
intelligence are progressively taking the place of human responses,
which are being replaced by this type of software. Since that time, These chatbots recognise particular terms and respond accordingly.
they have advanced to the point that they are now accurate and The Chatbot uses algorithms, artificial intelligence, and user-specific
flawless copies of humans. A computer programme that allows for phrases to choose the best response. When research project keywords
easier communication between a user and a chatbot is referred to as coincide, these bots will fail [10]. Imagine this: A user asks how to set
a chatbot [2-4]. It is a form of virtual assistant that has lately become up mobile auto-login authentication. The bot may use "auto" and
highly popular, mostly as a result of significant breakthroughs in "login" to choose the best response.
artificial intelligence and machine learning as well as other
fundamental domains such as neural networks and natural language
ii. Menu Bar/Button-Based Chatbots
processing. The popularity of this sort of virtual assistant has risen
significantly in recent years. By asking participants in the Menu-based bots will display buttons and drop-down menus, which
conversation thought-provoking
Authorized questions,
licensed use limited these
to: Zhejiang chatbots
University. make theon January
Downloaded 23,2025 at 17:01:42 UTC from IEEE Xplore. Restrictions apply.
are extensively used and already available in their most basic
versions. Decision-tree chatbots give choices to help users achieve
the best conclusions [7-9]. The user is instructed to choose their own
options and consider the AI's suggestions. Menu-based bots can
sometimes respond, despite their slower performance.
iii. Contextual Chatbots

Contextual is one of the most innovative chatbots available. They use

voice recognition and speech-to-text algorithms to decipher consumer
emotions [11]. This form of bot analyses the database to determine the
user's intents and respond intelligently. The bot learns and improves
through encounters. Food delivery bots operate. The database stores
the user's payment history, preferences, and delivery address. This
type of chatbot assesses the user's perspective and makes
recommendations based on past orders and preferences [12].
Figure:1 Errors organizations have encountered using chatbots

B. SYSTEM ARCHITECTURE
II. LITERATURE SURVEY:

It uses machine learning, internet banking, and latest AI patterns and

activations. It analyses the current AI trends and activates and
proposes alternate theories of change in some of the most commonly
accepted postulates. Privacy, Technological innovation, Biometrics
(access control), Virtual assistants, Authentication, Banking,
Chatbots. It discusses privacy issues and AI's effects on banking. Not
hands-free [13,14]. This article discusses how Indian commercial and
public sector banks use chatbots and virtual assistants. Banks buy
technologies. Transactions and queries are limited. This article Figure :2: Existing System Architecture
concerns AI chatbots. Chat bots are software that acts as a help desk
to solve difficulties individuals encounter in this bot. It uses Online III. PROPOSED SYSTEM:
banking, Face recognition, Speech recognition Help desk, not online AI-powered bank chat and voice assistant. It simulates human
transactions. Voiceless features[15,16]. discussions via text or audio. Text and voice aides have evolved
Remember IVR customer care and support for computer and mobile greatly. Machine learning and natural language processing allow
service issues? It was fascinating to watch folks use our portable these assistants to "learn" from prior interactions and have human-
devices and the words on the display panel to express their worries. like conversations, making them more "human." These helpers may
However, not all customer service plans went smoothly and calculate loan interests and check transaction information, among
effectively. The biggest fear was that most IVR systems could rapidly other functions.
learn or solve problems. They could not learn new abilities like
A financial chatbot shouldn't be limited to the customer's name.
computerised voice assistants. Smart card systems are another option.
Chatbots can alter the bank's marketing using its massive data set.
Smart cards are easy to lose or steal. Many smart card-based systems
Chatbots may market to client needs instead of randomly. "Every
use knowledge-based authentication to avoid impersonation if a card
Bank Requires a Chatbot for Digital Transformation" shows that
is lost, stolen, or compromised [17]. Typing was ineffective for most
chatbots are crucial for bank digital transformation.
typical situations. Simple errands were hard when we were younger.
i. Data storage and management
Changed recently. Without voice-driven AI services, implementing
intelligent virtual assistants would be slow, inefficient, and difficult.
They help us make informed decisions and solve problems in seconds. Banks have extensive client data. However, the material is so
disorganised that customer care personnel must travel through several
A. LIMITATIONS OF THE EXISTING SYSTEM:
files and directories before understanding the query. Chatbots can
collect, store, and organise data to make banking queries easier.
The banking industry is currently becoming more reliant on Chatbots can also guide customers. Chatbot data can be used for PFM.
information technology, and the utilisation of the most recent
technologies is becoming an increasingly important factor. On
ii. Avoids peak times
the other hand, there is a dearth of voice assistants in financial
institutions. Every financial institution has the ability to provide
Chatbots can help you avoid busy moments and save time by
services such as online banking, credit card services, and others
providing continual responses regardless of the amount of individuals
like them. In addition to providing business analytics and various asking information.
plans, financial institutions could also provide voice-enabled
services in an effort to encourage those who are illiterate to use
iii. Consistent Response Rate and Availability
their services. It merely serves as a help desk for customers.
There are no functions that are compatible with voice input, and
internet transactions are not supported. Chatbots also assist us maintain consistent response rates and
timeframes for your organisation during peak periods. This benefits

Authorized licensed use limited to: Zhejiang University. Downloaded on January 23,2025 at 17:01:42 UTC from IEEE Xplore. Restrictions apply.
both parties greatly. Because these bots can work in large or small
numbers, you can improve your consumers' experience. Customers
won't wait long for answers.

iv. Lower Costs

Finally, chatbots will save your firm money. Each new hire costs
thousands of dollars to recruit and train. Chatbots can handle more
customer conversations at reduced expense. This means you would
need fewer customer service staff. This also allows your live agents Figure: 7: Atm
to focus on higher-value prospects, benefiting your company.

A. SYSTEM ARCHITECTURE:

Figure: 8:Available loans

C. ACCURACY:

Figure: 3: Proposed System Architecture

Figure: 9:Accuracy
:

D. GRAPHICAL REPRESENTATION OF EFFICIENCY:

Figure: 4:Interface

Figure: 10 Comparative Analysis of Proposed method

Figure: 5:Statements

Figure: 6:Saving Plans

Authorized licensed use limited to: Zhejiang University. Downloaded on January 23,2025 at 17:01:42 UTC from IEEE Xplore. Restrictions apply.
 System”, Applied Sciences , Appl. Sci. 2023, 13, 3970.
https://doi.org/10.3390/app13063970.
[8]. IBM Cloud Education, ―Chatbots‖. [Online]. Available:
https://www.ibm.com/cloud/learn/chatbots-explained#toc-building-
a-pWei9Ux1
[9]. GhatteSaquid Nisar Parvin and KaziFaizan Farook Farida,
―Chatting Bot Service Provider‖. [Online]. Available:
http://www.aiktcdspace.org:8080/jspui/bitstream/123456789/2051/
1/aiktcDspace2051
[10]. Ajmeera Kiran And N Shirisha, “K-Anonymization Approach For
Privacy Preservation Using Data Perturbation Techniques In Data
Mining”, Materials Todays ,
Https://Doi.Org/10.1016/J.Matpr.2022.05.117,2022.
Figure: 11 Customer Satisfaction Analysis
[11]. Ajmeera Kiran And D. Vasumathi, “Optimal Privacy Preserving
Technique Over Big Data Analytics Using Oppositional Fruitfly
IV. CONCLUSION: Algorithm”, Recent Patents On Computer Science, Volume 13 ,
A "chatbot" is software that mimics human dialogue or converses Issue 2 , 2020, DOI : 10.2174/2213275911666181119113913.
with people. They listen and give thoughtful, detailed responses. [12]. Ajmeera Kiran and D. Vasumathi, “A Comprehensive Survey on
Speech-activated digital assistants are available alongside Privacy Preservation Algorithms in Data Mining”, Proceedings of
chatbots. Chatbots are more conversational than digital or the 2017 IEEE International Conference on Computational
intelligent assistants, which perform user-helpful tasks. Because Intelligence and Computing Research (ICCIC-2017), 978-1-5090-
bank self-service offerings are often poor, most customers have 6621-6/17/$31.00 ©2017 IEEE.
low expectations. Customer must regularly call call centre to [13]. Sethukarasi T, Neelakandan S, Prakash M, Baburaj E (2023) An
complete self-service transaction. Banks may benefit from voice Efficient Hybrid Job Scheduling Optimization (EHJSO) approach to
enhance resource search using Cuckoo and Grey Wolf Job
bots. It enables phone independence. They can be watched
Optimization for cloud environment. PLoS ONE 18(3): e0282600.
anywhere without deployment or space.
https://doi.org/10.1371/journal.pone.0282600
[14]. S. Ancy “Online Learning Model For Handling Different Concept
REFERENCES: Drifts Using Diverse Ensemble Classifiers,” cybernetics and
Systems”, Vol.50 Issue 7, 2019
[1]. Conversation-to Automation in Banking Through Chatbot Using
[15]. K.Devi, "Multi-level Fault tolerance Aware Scheduling Technique
Artificial Machine Intelligence Language By Silvia García-
MéndezatlanTTic, Information Technology Group, School of in a cloud environment", Journal of Internet Technology, Vol.22,
Telecommunications Engineering Milagros Fernández- Issue 1, pp 109-119, Jan ,2021
GavilanesDefense University Center, Pontevedra, Spain on 14 [16]. L. Maria Michael Visuwasam "A Distributed Intelligent Mobile
march 2018 [Online]. Available: Application For Analyzing Travel Big Data Analytics". Journal Of
https://ieeexplore.ieee.org/document/9197825
Peer To Peer Networking And Applications, 2019
[2]. P. Dileep Kumar Reddy, R. Praveen Sam, C. Shoba Bindu
“Optimal Blowfish Algorithm based Technique for Data Security [17]. Devi, K, Muthusenthil, B, Deep Learning Based Security Model for
in Cloud”Int. J. Business Intelligence and Data Mining, ISSN Cloud based Task Scheduling,"KSII Transactions on Internet and
online 1743-8195, ISSN print 1743-8187, Vol. 11, No. 2, Information", Vol.14, Issue 9,pp 3663-3679, Sept.2020
2016.Pp.171–189.DOI: 10.1504/IJBIDM.2016.10001484. (Inder
Science)(UGC Approved). Journal No: 16481
[3]. P. Dileep Kumar Reddy, R. Praveen Sam, C. Shoba Bindu
“Tripartite partite key assignment scheme for security of cloud data
classes” Journal of Theoretical and Applied Information
Technology, 15th July 2017. Vol.95. No 13, ISSN: 1992-8645, E-
ISSN: 1817-3195, Pg.No:3116-3126.(Scopus& UGC), Journal No:
23566.
[4]. G. Ramu, P. Dileep Kumar Reddy, Appawala Jayanthi “A Survey
of Precision Medicine Strategy Using Cognitive Computing”
International Journal of Machine Learning and Computing, Vol. 8,
No. 6, December 2018 DOI: 10.18178/IJMLC2018.8.6.741
(Scopus) (UGC Approved) Journal No: 48748, pp 530 to 535.
[5]. T. Sakthivel , Allam Balaram ,"The impact of mobility models on
geographic routing in multi-hop wireless networks and extensions
- a survey ," International Journal of Computer Networks and
Applications, Vol. 8, Issue No. 5 , pp. 634–670, 2021. DOI:
10.22247/ijcna/2021/209993.
[6]. Allam Balaram, Shaik Abdul Nab" A hybrid approach of
segmentation in brain tumor data using fuzzy c-means and level set
," Journal of Advanced Research in Dynamical and Control
Systems, Vol. 12, Issue No. 6, pp. 47–56, 2020. DOI:
10.5373/JARDCS/V12I6/S20201006.
[7]. P. Chinnasamy, Ashwag Albakri , Mudassir Khan, A. Ambeth Raja
, Ajmeera Kiran , Jyothi Chinna Babu “Smart Contract-Enabled
Secure Sharing of Health Data for a Mobile Cloud-Based E-Health

Authorized licensed use limited to: Zhejiang University. Downloaded on January 23,2025 at 17:01:42 UTC from IEEE Xplore. Restrictions apply.