Scribd
Upload
624 views8 pages

Credit Card Fraud Detection

This document discusses a project to use Hidden Markov Models to detect credit card fraud. The project team includes Bhushan Talekar, Rikesh Shah, and Saurabh Sarode, guided by Prof. Sainath Patil. The goal is to model credit card transaction sequences and detect fraud in online purchases without rejecting genuine transactions. The plan includes requirement analysis, modeling system behavior, algorithm study, coding, and testing. The process flow and reasons for using HMM are described. Results show 80% accuracy, ability to detect online frauds, and ensuring genuine transactions are not rejected. Design parameters like threshold, sequence length, and states influence fraud detection time and false positives.

Uploaded by

Rikesh Shah
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
624 views8 pages

Credit Card Fraud Detection

This document discusses a project to use Hidden Markov Models to detect credit card fraud. The project team includes Bhushan Talekar, Rikesh Shah, and Saurabh Sarode, guided by Prof. Sainath Patil. The goal is to model credit card transaction sequences and detect fraud in online purchases without rejecting genuine transactions. The plan includes requirement analysis, modeling system behavior, algorithm study, coding, and testing. The process flow and reasons for using HMM are described. Results show 80% accuracy, ability to detect online frauds, and ensuring genuine transactions are not rejected. Design parameters like threshold, sequence length, and states influence fraud detection time and false positives.

Uploaded by

Rikesh Shah
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 8

CREDIT CARD FRAUD DETECTION

MEMBERS :

B H U S H A N TA L E K A R RIKESH SHAH SAURABH SARODE

Guided By :Prof. SAINATH PATIL

Problem statement:To model sequence of operations in credit card transaction processing, using HIDDEN MARKOV MODEL(HMM) in order to detect frauds in online purchases. Also ensure that genuine transactions are not rejected.

Need For Doing This Project.????


Advancement in the e-commerce technology. Use of virtual card

PROJECT PLANNING

Requirement gathering and analysis.

Modeling system behavior.


Study of algorithms . - K-Means Clustering Algorithm. - Baum-Welch Algorithm. Coding.

Testing.

Process Flow Of Proposed System.

Why (Hidden markov Model) HMM ??

I.
II.

Requirement Of Labeled data for transactions .


Unable to detect new frauds.

III. Base rate fallacy effect.

Results
I. Testing credit card FDS using real data set is a difficult task as bank do not ,in general , agree to share data. II. The accuracy of the system is close to 80% over a wide variation in input data. III. By using HMM process we are able to detect frauds in

online transactions also ensured the customer that their


genuine transactions are not rejected.

Influence of Design Parameters


FP(False Positive) shows a clear trend of decreasing with higher threshold and smaller sequence lengths. However new states does not have a strong influence either on TP(True Positive) and FP. Fraud detection time & training time increases with the sequence length.

References :1. Abhinav Srivastava ,Credit Card Fraud Detection Using Hidden Markov Model , IEEE TRANSACTIONS ON DEPENDABLE AND SECURE COMPUTING, vol. 05, no. 1, JANUARY-MARCH 2008, pp. 37-48.

2. W. Fan, A.L. Prodromidis, and S.J. Stolfo, Distributed Data Mining in Credit Card Fraud Detection, IEEE Intelligent Systems,vol. 14, no. 6, pp. 67-74, 1999.
3. L.R. Rabiner, A Tutorial on Hidden Markov Models and Selected Applications in Speech Recognition, Proc. IEEE, vol. 77, no. 2, pp. 257-286, 1989. 4. Kaufman and P.J. Rousseeuw, Finding Groups in Data: An Introduction to Cluster Analysis, Wiley Series in Probability and Math. Statistics, 1990.

You might also like