Academic Journal of Business & Management, 2025, 7(7); doi: 10.25236/AJBM.2025.070703.
Yuan Yan1,2, Yujian Cui3, Sheng Zhou4, Ling Zhao5
1School of Business, Central South University of Forestry and Technology, Changsha, China
2Collaborative Innovation Center, Hunan Automotive Engineering Vocational University, Zhuzhou, China
3School of Management, Hunan Automotive Engineering Vocational University, Zhuzhou, China
4School of Continuing Education, Hunan Automotive Engineering Vocational University, Zhuzhou, China
5Changsha Commerce & Tourism College, Changsha, China
In capital markets, Special Treatment (ST) designation for listed companies stems from multiple complex factors. To enable early ST risk identification, this study explores integrated machine learning methods combining feature selection and predictive models, focusing on comparative evaluation of feature selection techniques through empirical analysis. Using a sample of 430 Chinese A-share listed firms with financial/non-financial indicators, 35 key indicators distinguishing distressed vs. healthy firms are first identified via statistical screening.We propose an innovative "LRRF-MIC Integrated Screening Method" integrating Lasso regression, Recursive Feature Elimination (RFE), Random Forest (RF), and Maximal Information Coefficient (MIC). This hybrid framework generates multi-dimensional feature evaluations and visual analytics, systematically selecting 14 core predictive indicators based on established criteria. Empirical validation uses these features as inputs for MLP and gcForest models, compared with benchmark models using raw data. Results show the LRRF-MIC framework outperforms single methods (RF, RFE, MIC, Lasso) by over 8% in prediction accuracy on average and benchmark models by 13%, demonstrating the efficacy and innovation of the proposed integrated approach.
Special Treatment (ST) Risk, Feature Selection, Machine Learning Models, LRRF-MIC Method
Yuan Yan, Yujian Cui, Sheng Zhou, Ling Zhao. Research on Feature Selection Method for Enterprise Financial Crisis Early Warning Based on LRRF-MIC Integrated Screening Approach. Academic Journal of Business & Management (2025), Vol. 7, Issue 7: 18-27. https://doi.org/10.25236/AJBM.2025.070703.
[1] Abdalzaher M.S., Soliman M.S., El-Hady S.M., Benslimane A., Elwekeil M. A deep learning model for earthquake parameters observation in IoT system-based earthquake early warning. IEEE Internet of Things Journal, 2021,9(11):8412-8424.
[2] Altman E.I. Financial ratios, discriminant analysis and the prediction of corporate bankruptcy. Journal of Finance, 1968,23(4):589-609.
[3] Dastkhan H. Network-based early warning system to predict financial crisis. International Journal of Finance & Economics, 2021,26(1):594-616.
[4] Jemović M., Marinković S. Determinants of financial crises—An early warning system based on panel logit regression. International Journal of Finance & Economics, 2021,26(1):103-117.
[5] Tsai C.F., Sue K.L., Hu Y.H., Chiu A. Combining feature selection, instance selection, and ensemble classification techniques for improved financial distress prediction. Journal of Business Research, 2021,130:200-209.
[6] Wu D., Ma X., Olson D.L. Financial distress prediction using integrated Z-score and multilayer perceptron neural networks. Decision Support Systems, 2022,159:113814.
[7] Yanli Z., Xiaolin Y., Wei Q., Yuhan Z., Juntao L. LASSO-based early warning of enterprise's financial crisis and the selection of key indicators. Journal of Henan Normal University (Natural Science Edition), 2016,44(3):1-8.
[8] Yao G., Hu X., Wang G. A novel ensemble feature selection method by integrating multiple ranking information combined with an SVM ensemble model for enterprise credit risk prediction in the supply chain. Expert Systems with Applications, 2022,200:117002.
[9] Yim J., Mitchell H. A comparison of corporate failure models in Australia: Hybrid neural networks, logit models and discriminant analysis. Paper presented at: International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems, 2003.
[10] Zhou Z.H., Feng J. Deep forest: Towards an alternative to deep neural networks. Paper presented at: Twenty-Sixth International Joint Conference on Artificial Intelligence, 2017.
[11] Huang H., Xu Q.G., Zhang Y.Q., Shi H.W. Financial crisis warning model based on KPCA dimension reduction and weight-LSSVM. Statistics & Decision, 2020,(20):157-161.
[12] Tan Y.Y., Chen J.Y., Sun J. Research on financial crisis warning of listed companies based on CNN. Journal of Southwest China Normal University (Natural Science Edition), 2021,46(5):88-95.
[13] Wu C., Chen X.F., Miao B.W. Research on financial crisis prediction of IT listed companies considering financial network indicators. Operations Research and Management Science, 2023,32(8):159-165.
[14] Wu Z.Y., Jin L.M., Han X.L., Wang Z.L., Wu B. Financial crisis warning model for foreign trade enterprises based on SMOTE-XGBoost. Computer Engineering and Applications, 2024,60(11):281-289.
[15] Zhang L., Liu J.P., Tian D.M. Financial early warning application based on Stacking-Bagging-Vote multi-source information fusion model. Journal of Computer Applications, 2022,42(1):280-286.
[16] Zhao J. Research on financial crisis warning model of listed companies based on logistic and Cox regression models. China Collective Economy, 2023,(10):95-98.