Predicting financial distress of Vietnamese listed companies using machine learning

  • Giang, Thi Thu Huyen
  • Do, Thi Van Trang
  • Doan, Viet Thang
  • Hoang, Thi Ngoc Anh
  • Nguyen, Thi Hong
  • Le, Duc Minh
  • Nguyen, Thi Thanh
  • Nguyen, Minh Thuy Tien
Keywords: Financial distress, Machine learning, Multiple regression model, LASSO, Generalized additive model, Random Forests, Gradient Boosting Regression Trees, Neural Network

Abstract

This study utilizes the traditional statistical method and machine learning methods to forecast the level of financial distress of listed companies in Vietnam. The data used in the study was collected from 646 listed companies on the HOSE and HNX exchanges during the period 2012-2022. The study experiments with the dataset on 6 machine learning models: Multiple Regression Model (MRL), LASSO, Generalized Additive Model (GAM), Random Forests (RF), Gradient Boosting Regression Trees (GBRT), and a single-layer, feed-forward neural network (NN), as well as the traditional statistical method. The research results demonstrate a congruence between the outcomes of the traditional method and modern machine learning models. Among these, the model with the highest accuracy is Random Forest (RF) with an accuracy rate of 98.8%. The variables that most influence the financial distress status of companies are TANG, ROA, LTD, NPM. Based on these results, our study proposes recommendations to support informed and effective financial decisions for stakeholders (companies, regulatory agencies, shareholders, creditors, investors).

điểm /   đánh giá
Published
2024-10-21
Issue
No. 270 (2024)
Section
Bài viết