User Tools

Site Tools


Action unknown: copypageplugin__copy
projects:year2:13.4

13.4 - A Spatio-Temporal Data Mining Approach for Fraud Detection

Project - Summary

Objectives:

The objective of this project was to develop a scalable spatio-temporal data mining framework for fraud detection. To accomplish this, we (a) developed new algorithms to detect anomalies (outliers) based on spatio-temporal context, (b) adapted sophisticated partitioning methods for parallelization to achieve scalability, and © applied pruning strategy to improve efficiency.

Project - Team

Team Member Role Email Phone Number Academic Site/IAB
Jian Chen PI Not available Not available UL Lafayette
Ryan Benton Co-PI Not available Not available UL Lafayette
Raju Gottumukkala Co-PI Not available Not available UL Lafayette
Shaaban Abbady Graduate Student Not available Not available UL Lafayette
Maria Duggimpudi Graduate Student Not available Not available UL Lafayette

Project - Impact and Uses/Benefits

Fraud is already a severe problem to both public and private sectors. This project provides a scalable spatio-temporal data mining approach for fraud detection in the big data era. Though further enhancement and customization is necessary prior to applying it into different use cases for fraud detection, given fraudulent activities are more and more sophisticated and definitely domain specific.

This system can be extended to other domains for a more generalized problem – anomaly (outlier) detection – such as financial data analysis, public safety surveillance, mechanical failure detection, and personal health monitoring, etc.

Project - Deep Dive

Project - Documents

FilenameFilesizeLast modified
13.4_year_2_ip_disclosure_letter.pdf1004.5 KiB2019/08/22 11:13
13.4_year_2_presentation.pptx2.2 MiB2019/08/22 11:13
13.4_year2_final_project_report_combined.pdf5.1 MiB2019/08/22 10:12
projects/year2/13.4.txt · Last modified: 2019/08/22 10:14 by sally.johnson