Title: A study on financial early warning for technology companies incorporating big data and random forest algorithms

Authors: Xuemei Wang

Addresses: Department of Accounting and Finance, Shandong Foreign Trade Vocational College, Qingdao, Shandong, China

Abstract: This study establishes a model to predict the financial risk and the possibility of fraud of technology enterprises by using the random forest algorithm and SMOTE algorithm. By testing and identifying data sets, the model shows good accuracy and efficiency, with an ACC index of 97.2%, an accuracy of 96.8%, a recall rate of 1, and an F1 index of 98.4%. Compared with the traditional model, the ratio of cash income to main business income is the highest, which shows that the prediction accuracy of this model is obviously better than that of the traditional model. The results show that this model will have some practical value in evaluating the financial status of science and technology enterprises.

Keywords: financial fraud; financial malpractice; machine learning; random forest algorithm; SMOTE algorithm.

DOI: 10.1504/IJGUC.2024.140119

International Journal of Grid and Utility Computing, 2024 Vol.15 No.3/4, pp.343 - 351

Received: 08 Jun 2023
Accepted: 21 Nov 2023
Published online: 24 Jul 2024 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article