Financial Fraud Detection Using Deep Learning Based on Modified Tabular Learning

DOI

10.2991/978-94-6463-005-3_55How to use a DOI?

Keywords

Fraud Detection; Deep Learning; Neural Networks; Interpretability

Abstract

With the rapid development of Internet technology and the rapid progress of the financial industry, fraud is causing more and more damage, which not only brings huge losses to enterprises, but also has a significant impact on corporate image. Therefore, detecting fraud is an important topic. At present, there are roughly two methods to detect fraud. One is to establish corresponding standards in the financial field for manual detection. The defects of this method are slow detection speed, lagging update and high false positive rate. Another method is automatic recognition of the machine. However, the disadvantage of this method is that when the machine runs stably, too many will cause great pressure to the machine. Therefore, in recent years, with the application of artificial intelligence in the financial field, the application of artificial intelligence method in fraud detection has great potential. At present, the mainstream intelligent methods for fraud detection include convolutional neural network (CNN) and support vector regression (SVR). However, these methods are not interpretable in tabular data model, we proposed a feature-based deep learning regression model that can directly deal with tabular data. In order to verify the effectiveness of this model, we conducted an experiment on a real transfer record of a mobile payment company with the proposed method and mainstream method. The results show that the model has a good performance in detecting fraudulent behavior and verifies the feasibility of the model.

Copyright

© 2023 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Meiying Huang
AU  - Wenxuan Li
PY  - 2022
DA  - 2022/11/10
TI  - Financial Fraud Detection Using Deep Learning Based on Modified Tabular Learning
BT  - Proceedings of the 2022 3rd International Conference on E-commerce and Internet Technology (ECIT 2022)
PB  - Atlantis Press
SP  - 550
EP  - 558
SN  - 2589-4943
UR  - https://doi.org/10.2991/978-94-6463-005-3_55
DO  - 10.2991/978-94-6463-005-3_55
ID  - Huang2022
ER  -