Credit rating model for enterprises in Vietnam

Abstract:

The objective of this study is to develop an Artificial Neural Network (ANN) model for credit rating of small, medium and large enterprises in Vietnam during the period 2015- 2018. The dataset is obtained from the Orbis database, comprising more than 39,000 companies in Vietnam during the aforementioned period. The results indicate that the significant predictors of the credit rating model include net income to total assets (NITA), return on equity (ROE), current ratio, solvency ratio, company size (SIZELNNE), and GDP growth rate (GDPG). Additionally, this study ranked these predictors based on their importance, with solvency ratio being the most influential, followed by SIZELNNE, current ratio, NITA, GDPG, and ROE. These results suggest that the ANN model is the most effective model for credit rating, as it requires less input data and provides higher accuracy rates.