Leveraging Mixture of Experts and Deep Learning-Based Data Rebalancing to Improve Credit Fraud Detection

Credit card fraud detection is a critical challenge in the financial sector due to the rapidly evolving tactics of fraudsters and the significant class imbalance betweenegitimate and fraudulent transactions. Traditional models, while effective to some extent, often suffer from high false positive ra...

Full description

Saved in:
Bibliographic Details
Main Authors: Zeyuan Yang, Yixuan Wang, Haokun Shi, Qiang Qiu
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Big Data and Cognitive Computing
Subjects:
Online Access:https://www.mdpi.com/2504-2289/8/11/151
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846154340458299392
author Zeyuan Yang
Yixuan Wang
Haokun Shi
Qiang Qiu
author_facet Zeyuan Yang
Yixuan Wang
Haokun Shi
Qiang Qiu
author_sort Zeyuan Yang
collection DOAJ
description Credit card fraud detection is a critical challenge in the financial sector due to the rapidly evolving tactics of fraudsters and the significant class imbalance betweenegitimate and fraudulent transactions. Traditional models, while effective to some extent, often suffer from high false positive rates and fail to generalize well to emerging fraud patterns. In this paper, we propose a novel approach that integrates a Mixture of Experts (MoE) model with a Deep Neural Network-based Synthetic Minority Over-sampling Technique (DNN-SMOTE) to enhance fraud detection performance. The MoE modeleverages multiple specialized expert networks, each trained to detect specific types of fraud, while the DNN-SMOTE generates high-quality synthetic samples to address the class imbalance. Our experimental results on a publicly available dataset demonstrate that the proposed method achieves a classification accuracy of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>99.93</mn><mo>%</mo></mrow></semantics></math></inline-formula>, a true positive rate of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>84.69</mn><mo>%</mo></mrow></semantics></math></inline-formula>, and a true negative rate of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>99.95</mn><mo>%</mo></mrow></semantics></math></inline-formula>. The Matthews Correlation Coefficient (MCC) of 0.7883 further highlights the model’s balanced performance in detecting fraudulent transactions. These results underscore the effectiveness of combining MoE with DNN-SMOTE, offering a robust solution for real-world credit card fraud detection scenarios.
format Article
id doaj-art-9705da76d0c54a43a025e508915469e3
institution Kabale University
issn 2504-2289
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Big Data and Cognitive Computing
spelling doaj-art-9705da76d0c54a43a025e508915469e32024-11-26T17:51:11ZengMDPI AGBig Data and Cognitive Computing2504-22892024-11-0181115110.3390/bdcc8110151Leveraging Mixture of Experts and Deep Learning-Based Data Rebalancing to Improve Credit Fraud DetectionZeyuan Yang0Yixuan Wang1Haokun Shi2Qiang Qiu3College of Economics and Management, Nanjing Forestry University, Nanjing 210037, ChinaDepartment of Computer Science, New York University, New York, NY 10012, USASchool of Computer Science, University of Sheffield, Sheffield S1 4DP, UKCollege of Economics and Management, Nanjing Forestry University, Nanjing 210037, ChinaCredit card fraud detection is a critical challenge in the financial sector due to the rapidly evolving tactics of fraudsters and the significant class imbalance betweenegitimate and fraudulent transactions. Traditional models, while effective to some extent, often suffer from high false positive rates and fail to generalize well to emerging fraud patterns. In this paper, we propose a novel approach that integrates a Mixture of Experts (MoE) model with a Deep Neural Network-based Synthetic Minority Over-sampling Technique (DNN-SMOTE) to enhance fraud detection performance. The MoE modeleverages multiple specialized expert networks, each trained to detect specific types of fraud, while the DNN-SMOTE generates high-quality synthetic samples to address the class imbalance. Our experimental results on a publicly available dataset demonstrate that the proposed method achieves a classification accuracy of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>99.93</mn><mo>%</mo></mrow></semantics></math></inline-formula>, a true positive rate of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>84.69</mn><mo>%</mo></mrow></semantics></math></inline-formula>, and a true negative rate of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>99.95</mn><mo>%</mo></mrow></semantics></math></inline-formula>. The Matthews Correlation Coefficient (MCC) of 0.7883 further highlights the model’s balanced performance in detecting fraudulent transactions. These results underscore the effectiveness of combining MoE with DNN-SMOTE, offering a robust solution for real-world credit card fraud detection scenarios.https://www.mdpi.com/2504-2289/8/11/151credit card fraud detectionfinancial securitymixture of expertsensembleearningsynthetic data generation
spellingShingle Zeyuan Yang
Yixuan Wang
Haokun Shi
Qiang Qiu
Leveraging Mixture of Experts and Deep Learning-Based Data Rebalancing to Improve Credit Fraud Detection
Big Data and Cognitive Computing
credit card fraud detection
financial security
mixture of experts
ensembleearning
synthetic data generation
title Leveraging Mixture of Experts and Deep Learning-Based Data Rebalancing to Improve Credit Fraud Detection
title_full Leveraging Mixture of Experts and Deep Learning-Based Data Rebalancing to Improve Credit Fraud Detection
title_fullStr Leveraging Mixture of Experts and Deep Learning-Based Data Rebalancing to Improve Credit Fraud Detection
title_full_unstemmed Leveraging Mixture of Experts and Deep Learning-Based Data Rebalancing to Improve Credit Fraud Detection
title_short Leveraging Mixture of Experts and Deep Learning-Based Data Rebalancing to Improve Credit Fraud Detection
title_sort leveraging mixture of experts and deep learning based data rebalancing to improve credit fraud detection
topic credit card fraud detection
financial security
mixture of experts
ensembleearning
synthetic data generation
url https://www.mdpi.com/2504-2289/8/11/151
work_keys_str_mv AT zeyuanyang leveragingmixtureofexpertsanddeeplearningbaseddatarebalancingtoimprovecreditfrauddetection
AT yixuanwang leveragingmixtureofexpertsanddeeplearningbaseddatarebalancingtoimprovecreditfrauddetection
AT haokunshi leveragingmixtureofexpertsanddeeplearningbaseddatarebalancingtoimprovecreditfrauddetection
AT qiangqiu leveragingmixtureofexpertsanddeeplearningbaseddatarebalancingtoimprovecreditfrauddetection