Comparative Analysis of the Predictive Power of Machine Learning Models for Forecasting the Credit Ratings of Machine-Building Companies

The purpose of this study is to compare the predictive power of different machine learning models to reproduce the credit ratings of Moody's assigned to machine-building companies. The study closes several gaps found in the literature related to the choice of explanatory variables and the formation of a sample of data for modeling. The task to be solved is highly relevant. There is a growing need for high-precision and low-cost models for reproducing the credit ratings of machine-building companies (internal credit ratings). This is due to the ongoing growth of credit risks of companies in the industry, as well as the limited number of assigned public ratings to these companies from international rating agencies due to the high cost of rating process. The study compares the predictive power of three machine learning models: ordered logistic regression, random forest, and gradient boosting. The sample of companies includes 109 enterprises of the machine-building industry from 18 countries for the period from 2005 to 2016. The financial indicators of companies that correspond to the industry methodology of Moody's and the macroeconomic indicators of the home countries of the companies are used as explanatory variables. The results show that among models studied the artificial intelligence models have the greatest predictive ability. The random forest model showed a prediction accuracy of 50%, the gradient boosting model showed accuracy of 47%. Their predictive power is almost twice as high as the accuracy of ordered logistic regression (25%). In addition, the article tested two different ways of forming a sample: randomly and taking into account the time factor. The result showed that the use of random sampling increases the predictive power of the models. The inclusion of macroeconomic variables into the models does not improve their predictive power. The explanation is that rating agencies follow a "through the cycle" rating approach to ensure the stability of ratings. The results of the study may be useful for researchers who are engaged in assessing the accuracy of empirical methods for modeling credit ratings, as well as practitioners in banking industry who directly use such models to assess the creditworthiness of machine-building companies.