Research Article
Manufacturing Companies Financial Fraud Detection Based on Interpretable Machine Learning
@INPROCEEDINGS{10.4108/eai.1-9-2023.2338768, author={Xiang Li and Xinyu Da and Wanxin Shi and Wenjun Liu}, title={Manufacturing Companies Financial Fraud Detection Based on Interpretable Machine Learning}, proceedings={Proceedings of the 2nd International Conference on Public Management, Digital Economy and Internet Technology, ICPDI 2023, September 1--3, 2023, Chongqing, China}, publisher={EAI}, proceedings_a={ICPDI}, year={2023}, month={11}, keywords={machine learning; financial fraud; detection framework; binary classification}, doi={10.4108/eai.1-9-2023.2338768} }- Xiang Li
Xinyu Da
Wanxin Shi
Wenjun Liu
Year: 2023
Manufacturing Companies Financial Fraud Detection Based on Interpretable Machine Learning
ICPDI
EAI
DOI: 10.4108/eai.1-9-2023.2338768
Abstract
Because of the industrial characteristics like complex purchasing and selling links in manufacturing companies, it is relatively easy for them to conduct financial fraud. Taking A-share manufacturing companies from 2009 to 2021 as an observation sample, this paper constructed a financial fraud detection feature set of manufacturing companies from five dimensions. By using 5 algorithms to build detection models and calculating the metrics, research found that XGBoost, LightGBM and Random Forest have better predictive performance. And the further parameterized features importance showed that indicators such as “ROA”, “Income receivable” and “Internal control index” have a significant guiding role in identifying financial fraud of Manufacturing Listed Corporations.
