Research Article
Research on the Identification of Whitewashing Degree of Financial Statements Based on Support Vector Machine Model
@INPROCEEDINGS{10.4108/eai.19-5-2023.2334389, author={Tingyu Luo}, title={Research on the Identification of Whitewashing Degree of Financial Statements Based on Support Vector Machine Model}, proceedings={Proceedings of the 2nd International Conference on Bigdata Blockchain and Economy Management, ICBBEM 2023, May 19--21, 2023, Hangzhou, China}, publisher={EAI}, proceedings_a={ICBBEM}, year={2023}, month={7}, keywords={degree of whitewashing of financial statements benford's law svm model excess-mad method}, doi={10.4108/eai.19-5-2023.2334389} }- Tingyu Luo
Year: 2023
Research on the Identification of Whitewashing Degree of Financial Statements Based on Support Vector Machine Model
ICBBEM
EAI
DOI: 10.4108/eai.19-5-2023.2334389
Abstract
Using the data of China capital market, select the financial statement data of A-share and B-share listed companies released from 2000 to 2021 as the overall data sample, and further screen out the 5% samples with the highest and lowest degree of financial whitewashing, a total of More than 8,000 pieces of data are used as data samples for research. Then first use the improved Excess-MAD algorithm based on Benford's law to establish the identification index of financial statement whitewashing, and then select 11 financial indicators from four theoretical analysis dimensions for kendall correlation analysis, and finally retain seven modeling indicators and establish the final SVM prediction model. The results of the model run show that the support vector machine model established through this process can well identify the company samples with a relatively higher degree of financial whitewashing.
