Fraud Detection in Mobile Money Transactions Using Machine Learning

Thumbnail Image
Date
2019-01-01
Authors
Kang, Haimeng
Major Professor
Anthony Townsend
Advisor
Committee Member
Journal Title
Journal ISSN
Volume Title
Publisher
Authors
Research Projects
Organizational Units
Organizational Unit
Information Systems and Business Analytics
In today’s business landscape, information systems and business analytics are pivotal elements that drive success. Information systems form the digital foundation of modern enterprises, while business analytics involves the strategic analysis of data to extract meaningful insights. Information systems have the power to create and restructure industries, empower individuals and firms, and dramatically reduce costs. Business analytics empowers organizations to make precise, data-driven decisions that optimize operations, enhance strategies, and fuel overall growth. Explore these essential fields to understand how data and technology come together, providing the knowledge needed to make informed decisions and achieve remarkable outcomes.
Journal Issue
Is Version Of
Versions
Series
Abstract

This study explores an effective data mining system for fraud detection in mobile financial transactions. Attempting two broad-used supervised machine learning models, random forest and gradient boosting, the study aims to test and compare their applicability in the detection of fraudulent records. Both classification models were developed using a synthetic dataset of mobile money transactions, which was generated based on a sample of real transactions extracted from an international mobile money service company.

Comments
Description
Keywords
Citation
DOI
Source
Subject Categories
Copyright
Tue Jan 01 00:00:00 UTC 2019