Babu Banarasi Das Engineering College, Lucknow

[AKTU College Code 508]

Major Project Presentation

AI Based Fraud Detection System For

Real Time Financial Transactions

Guide Name: Ms. Archana Dwivedi

Project ID: CSE/Project/2023/24

Team Members:
Name Roll Number Section
Anmol Chaubey 2005080100017 CSE-4
Anshuman Yadav 2005080100020 CSE-4
Anuj Kumar 2005080100021 CSE-4
 Babu Banarasi Das Engineering College, Lucknow
[AKTU College Code 508]

Content
• Abstract
• Introduction
• Literature Review
• Problem Statement
• Proposed Solution
• Technical Stack
• Conclusion & Future Scope
• References
 Babu Banarasi Das Engineering College, Lucknow
[AKTU College Code 508]

Abstract
As we all know in today’s world with day-to-day advancement in technologies,
Fraudsters are becoming more sophisticated and it is becoming increasingly difficult to
identify fraudulent activities without using artificial intelligence (AI) techniques. So,
we decided to work on making an “AI Based Fraud Detection System for Real Time
Financial Transactions” which is Effective and Secure as it predicts the possibility of
frauds in order to avoid them before they even occur. By creating this we are also using
and improving our knowledge to do some real-world application.
 Babu Banarasi Das Engineering College, Lucknow
[AKTU College Code 508]

Introduction
Through this project we try to improve our knowledge by practicing our caliber in
some real world website. We all know that how complicated, troublesome, vulnerable
this sector is. We decided to make a system that scan the operations for the traces of
fraudulent activities in a simple, secure and convenient manner. This project was built
keeping in mind about latest advancements in technology i.e. PYTHON, AI and
MACHINE LEARNING would also help people to freely and more easily use their
systems.
 Babu Banarasi Das Engineering College, Lucknow
[AKTU College Code 508]

Literature Review
• We reviewed the latest techniques to detect anomaly and trust relaying in IoT
environment. Also, we focused on reviewing the methods and algorithms to detect
financial fraud from traditional methods to the latest one. V. Sharma et al. proposed
a novel solution in the form of fission computing. The proposed approach relies on
the edge-crowd integration for maintenance of trust and preservation of privacy
rules in social IoT environment. They performed analysis through numerical
simulations by using a safe network and presented a case study on the detection of
fake news sources in social IoT environment .
• Also, a pervasive trust management framework is presented for Pervasive Online
Social Networks (POSNs), which is capable of generating high trust value between
the users with a lower cost of monitoring .
• As a solution to identify anomalies in IoT environment, a model was proposed on
the basis of cognitive tokens, which provide an Intelligent Sensing Model for
Anomalies (ISMA) detection by deliberately inducing faulty data to attract the
anomalous users .
 Babu Banarasi Das Engineering College, Lucknow
[AKTU College Code 508]

Problem Statement
• It is estimated that 10,000 transactions take place via credit cards every second
worldwide. Owing to such a high transaction frequency, credit cards have become the
primary targets of fraud.
• Fraud cases occur under different conditions, e.g., transactions at points of sale
(POSs) or transactions made online or over the telephone, i.e., card-not-present (CNP)
cases or transactions with lost and stolen cards.
• Designing a system for real-time financial transactions that uses AI to detect fraud is
the focus of this challenging problem statement.
 Babu Banarasi Das Engineering College, Lucknow
[AKTU College Code 508]

Proposed Solution
• An AI-based system for fraud detection is proposed. The system uses logistic
regression to build a classifier called the LogR classifier. The LogR classifier has
the ability to deal with imbalanced data and adapt to the behaviour of the user by
employing the cross-validation technique.
• To ensure high accuracy detection, two main methods are used to clean the data.
The mean-based method deals with missing values, and the clustering-based
method deals with outliers.
• Extensive experiments are conducted to train and test the proposed classifier using
a standard database .
 Babu Banarasi Das Engineering College, Lucknow
[AKTU College Code 508]

Technical Stack
 Babu Banarasi Das Engineering College, Lucknow
[AKTU College Code 508]

Technical Stack
 Babu Banarasi Das Engineering College, Lucknow
[AKTU College Code 508]

Conclusion & Future Scope

• The detection of credit card fraud is a vital research field. This is because of the increasing
number of fraud cases in financial institutions.
• This issue opens the door for employing artificial intelligence to build systems that can detect
fraud. Building an AI-based system to detect fraud requires a database to train the system (or
classifier).
• The data in reality are dirty and have missing values, noisy data, and outliers. Such issues
negatively affect the accuracy rate of the system. To overcome these problems, a logistic
regression-based classifier is proposed.
• The data are first cleaned using two methods: the mean-based method and clustering-based
method. Second, the classifier is trained based on the crossvalidation technique (folds=10),
which ensures that the whole database is used as both the training data set and testing data set.
 Babu Banarasi Das Engineering College, Lucknow
[AKTU College Code 508]

References

• https://medium.com/
• https://nextjs.org/docs
• https://platform.openai.com/docs/introduction
• https://stripe.com/docs
• https://tailwindcss.com/docs
• https://doclime.com
• https://chatdoc.com/blog/ChatDOC%20-%20The%20Bes
t%20PDF%20AI%20Chat%20App/
Babu Banarasi Das Engineering College, Lucknow
[AKTU College Code 508]

THANK YOU