A Financial Fraud Prediction Framework Based on Stacking Ensemble Learning

With the rapid development of the capital market, financial fraud cases are becoming increasingly common. The evolving fraud strategies pose significant threats to financial regulation, market order, and the interests of ordinary investors. In order to combine the generalization performance of diffe...

Full description

Saved in:
Bibliographic Details
Main Authors: Shanshan Zhu, Haotian Wu, Eric W. T. Ngai, Jifan Ren, Daojing He, Tengyun Ma, Yubin Li
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Systems
Subjects:
Online Access:https://www.mdpi.com/2079-8954/12/12/588
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850059987865305088
author Shanshan Zhu
Haotian Wu
Eric W. T. Ngai
Jifan Ren
Daojing He
Tengyun Ma
Yubin Li
author_facet Shanshan Zhu
Haotian Wu
Eric W. T. Ngai
Jifan Ren
Daojing He
Tengyun Ma
Yubin Li
author_sort Shanshan Zhu
collection DOAJ
description With the rapid development of the capital market, financial fraud cases are becoming increasingly common. The evolving fraud strategies pose significant threats to financial regulation, market order, and the interests of ordinary investors. In order to combine the generalization performance of different machine learning methods and improve the effectiveness of financial fraud prediction, this paper proposes a novel financial fraud prediction framework based on stacking ensemble learning. This framework, based on data from listed companies, comprehensively considers financial ratio indicators and non-financial indicators. It uses the stacking ensemble technique to integrate numerous base models of machine learning algorithms for predicting financial fraud. Furthermore, the proposed framework has high versatility and is suitable for various tasks related to financial fraud prediction, addressing the problem of model selection difficulties in previous research due to different scenarios and data. We also conducted case studies on specific companies and industries, confirming the significant interpretability and practical applicability of the proposed framework. The results show that the recall rate and Area Under Curve (AUC) of our framework reached 0.8246 and 0.8146, respectively, surpassing mainstream machine learning models such as XGBoost and LightGBM in existing studies. This research study is of great significance for predicting the increasing number of financial fraud cases, providing a reliable tool for financial regulatory institutions and investors.
format Article
id doaj-art-8ae2b71f498d41c4968b8c2838f5da56
institution DOAJ
issn 2079-8954
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Systems
spelling doaj-art-8ae2b71f498d41c4968b8c2838f5da562025-08-20T02:50:43ZengMDPI AGSystems2079-89542024-12-01121258810.3390/systems12120588A Financial Fraud Prediction Framework Based on Stacking Ensemble LearningShanshan Zhu0Haotian Wu1Eric W. T. Ngai2Jifan Ren3Daojing He4Tengyun Ma5Yubin Li6School of Economics and Management, Harbin Institute of Technology, Shenzhen 518000, ChinaFaculty of Computer, Harbin Institute of Technology, Harbin 150001, ChinaDepartment of Management and Marketing, The Hong Kong Polytechnic University, Hong Kong 00852, ChinaSchool of Economics and Management, Harbin Institute of Technology, Shenzhen 518000, ChinaSchool of Computer Science and Technology, Harbin Institute of Technology, Shenzhen 518000, ChinaSchool of Computer Science and Technology, Harbin Institute of Technology, Shenzhen 518000, ChinaSchool of Economics and Management, Harbin Institute of Technology, Shenzhen 518000, ChinaWith the rapid development of the capital market, financial fraud cases are becoming increasingly common. The evolving fraud strategies pose significant threats to financial regulation, market order, and the interests of ordinary investors. In order to combine the generalization performance of different machine learning methods and improve the effectiveness of financial fraud prediction, this paper proposes a novel financial fraud prediction framework based on stacking ensemble learning. This framework, based on data from listed companies, comprehensively considers financial ratio indicators and non-financial indicators. It uses the stacking ensemble technique to integrate numerous base models of machine learning algorithms for predicting financial fraud. Furthermore, the proposed framework has high versatility and is suitable for various tasks related to financial fraud prediction, addressing the problem of model selection difficulties in previous research due to different scenarios and data. We also conducted case studies on specific companies and industries, confirming the significant interpretability and practical applicability of the proposed framework. The results show that the recall rate and Area Under Curve (AUC) of our framework reached 0.8246 and 0.8146, respectively, surpassing mainstream machine learning models such as XGBoost and LightGBM in existing studies. This research study is of great significance for predicting the increasing number of financial fraud cases, providing a reliable tool for financial regulatory institutions and investors.https://www.mdpi.com/2079-8954/12/12/588financial statementfraud predictionmachine learningstacking model
spellingShingle Shanshan Zhu
Haotian Wu
Eric W. T. Ngai
Jifan Ren
Daojing He
Tengyun Ma
Yubin Li
A Financial Fraud Prediction Framework Based on Stacking Ensemble Learning
Systems
financial statement
fraud prediction
machine learning
stacking model
title A Financial Fraud Prediction Framework Based on Stacking Ensemble Learning
title_full A Financial Fraud Prediction Framework Based on Stacking Ensemble Learning
title_fullStr A Financial Fraud Prediction Framework Based on Stacking Ensemble Learning
title_full_unstemmed A Financial Fraud Prediction Framework Based on Stacking Ensemble Learning
title_short A Financial Fraud Prediction Framework Based on Stacking Ensemble Learning
title_sort financial fraud prediction framework based on stacking ensemble learning
topic financial statement
fraud prediction
machine learning
stacking model
url https://www.mdpi.com/2079-8954/12/12/588
work_keys_str_mv AT shanshanzhu afinancialfraudpredictionframeworkbasedonstackingensemblelearning
AT haotianwu afinancialfraudpredictionframeworkbasedonstackingensemblelearning
AT ericwtngai afinancialfraudpredictionframeworkbasedonstackingensemblelearning
AT jifanren afinancialfraudpredictionframeworkbasedonstackingensemblelearning
AT daojinghe afinancialfraudpredictionframeworkbasedonstackingensemblelearning
AT tengyunma afinancialfraudpredictionframeworkbasedonstackingensemblelearning
AT yubinli afinancialfraudpredictionframeworkbasedonstackingensemblelearning
AT shanshanzhu financialfraudpredictionframeworkbasedonstackingensemblelearning
AT haotianwu financialfraudpredictionframeworkbasedonstackingensemblelearning
AT ericwtngai financialfraudpredictionframeworkbasedonstackingensemblelearning
AT jifanren financialfraudpredictionframeworkbasedonstackingensemblelearning
AT daojinghe financialfraudpredictionframeworkbasedonstackingensemblelearning
AT tengyunma financialfraudpredictionframeworkbasedonstackingensemblelearning
AT yubinli financialfraudpredictionframeworkbasedonstackingensemblelearning