Scribd
Upload
315 views

Sree Vahini: Codetect Financial Fraud Detection With Anomaly Feature Detection

This document presents a proposed financial fraud detection framework called CoDetect that uses both network and feature information. It aims to simultaneously detect fraudulent activities and identify patterns associated with the fraud. The existing system focuses only on network or feature data separately. CoDetect is an unsupervised model that performs co-factorization of matrices representing genuine properties of financial data. It provides a better understanding of fraud patterns and helps trace the origin of fraudulent groups. The proposed system develops a novel framework considering the special demands of detecting and tracing fraudulent entities and behaviors.

Uploaded by

kkvprasad
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
315 views

Sree Vahini: Codetect Financial Fraud Detection With Anomaly Feature Detection

This document presents a proposed financial fraud detection framework called CoDetect that uses both network and feature information. It aims to simultaneously detect fraudulent activities and identify patterns associated with the fraud. The existing system focuses only on network or feature data separately. CoDetect is an unsupervised model that performs co-factorization of matrices representing genuine properties of financial data. It provides a better understanding of fraud patterns and helps trace the origin of fraudulent groups. The proposed system develops a novel framework considering the special demands of detecting and tracing fraudulent entities and behaviors.

Uploaded by

kkvprasad
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 26

SREE VAHINI

INSTITUTE OF SCIENCE AND TECHNOLOGY

CODETECT FINANCIAL FRAUD DETECTION


WITH ANOMALY FEATURE DETECTION
NAME: ROLL NO: PROJECT GUIDE :
P. KALYANI (16MG1A0579) P.SOMARAJU M.Tech
T.K.K.V.PRASAD (17MG5A0506) Assist.Professor
A.GANGA BHAVANI (16MG1A0553)
CH.BHARGAV REDDY (16MG1A0588)
CONTENTS
● ABSTRACT
● EXISTING AND PROPOSED SYSTEM
● SOFTWARE REQUIREMENT SPECIFICATION
● MODULES
● UML DIAGRAMS
● TEST CASES
● OUTPUT SCREENS
● CONCLUSION
● REFERENCES
ABSTRACT
Financial fraud, such as money laundering, is
known to be a serious process of crime that makes
illegitimately obtained funds go to terrorism or other
criminal activity. This kind of illegal activities involve
complex networks of trade and financial transactions,
which makes it difficult to detect the fraud entities and
discover the features of fraud. However, the majority of
existing methods focus on networks or features
information separately, which does not utilize both
information. In this paper, we propose a novel fraud
detection framework, Co-Detect, which can leverage both
network information and feature information for financial
fraud detection. In addition, the CoDetect can
simultaneously detecting financial fraud activities and the
feature patterns associated with the fraud activities.
ANALYSIS
EXISTING SYSTEM
❖ CoDetect is an unsupervised model which is based on
matrices co factorization. The matrices from graph
represent the genuine proprieties (features and
connections) of financial data.
❖ The detection results give a better understanding of
fraud patterns and furthermore, help to trace the
originate of fraud groups.
DISADVANTAGES
• There is no Evaluation with Subspace Clustering
Methods.
• There is no SVM Classification in Credit Card
Fraud Detections.
PROPOSED SYSTEM:
❖ In the proposed system, the system would like to develop a
novel framework for fraud detection by considering the special
detecting and tracing demanding of fraud entities and
behaviors.
❖ Specifically, we investigate:
❖ (1) how to utilize both graph matrix and feature matrix for
fraud detection and fraud tracing;
ADVANTAGES
• Provide an approach to establish weighted graph from financial
network, incorporating properties of nodes and links.
•  Propose patterns discovery and anomaly features identification,
employing
• Evaluate framework using synthetic and real world data to
demonstrate both effectiveness and efficiency of the proposed
framework.
SOFTWARE REQUIREMENTS SPECIFICATION

HARDWARE REQUIREMENTS

Processor - Pentium –IV


RAM - 4 GB (min)
Hard Disk - 20 GB
Key Board - Standard Windows Keyboard
Mouse - Two or Three Button Mouse
Monitor - SVGA

SOFTWARE REQUIREMENTS

Operating System - Windows XP


Coding Language - Java/J2EE(JSP,Servlet)
Front End - J2EE
Back End - MySQL
MODULES
● ADMIN
● USER
● TRANSPORTATION COMPANY
ARCHITECTURE:
DESIGN:
• UML DIAGRAMS
• E-R DIAGRAM
SEQUENCE DIAGRAM:
DATAFLOW DIAGRAM:
USECASE DIAGRAM:
CLASS DIAGRAM:
E-R DIAGRAM:
TEST CASES
HOME PAGE
ADMIN LOGIN
ADMIN PROFILE
USER LOGIN
USER PROFILE
TRANSPORT COMPANY LOGIN
TRANSPORT COMPANY PROFILE
CONCLUSION
We propose a new framework, Co Detect, which can
perform fraud detection on graph-based similarity matrix
and feature matrix simultaneously. It introduces a new way
to reveal the nature of financial activities from fraud
patterns to suspicious property. Furthermore, the
framework provides a more interpretable way to identify
the fraud on sparse matrix. Experimental results on
synthetic and real world data sets show that the proposed
framework (Co Detect) can effectively detect the fraud
patterns as well as suspicious features. With this co-
detection framework, executives in financial supervision
can not only detect the fraud patterns but also trace the
original of fraud with suspicious feature. Financial activities
are involving with time. We can represent these activities
into similarity tensor and feature tensor. So we would like to
study how to integrate tensor into co-detect framework for
fraud detection.
REFERENCES
[1] C. Sullivan, and E. Smith, Trade-based money laundering:
Risks and regulatory responses. AIC Reports Research and
Public
Policy Series, 115.
[2] Trade-based money laundering flourishing. United Press
Internatinoal, May, 2009. http://www.upi.com/Top
News/2009/05/11/Trade-based-money-laundering-
flourishing/UPI-17
331242061466.
[3] L. Akoglu, M. McGlohon, and C. Faloutsos, Oddball:
Spotting
anomalies in weighted graphs. In PAKDD, pp:410-421, 2010.

You might also like