Logit model for predicting the probability of default for Russian small and medium-sized enterprises

Abstract

Subject. This article deals with the issues of determining the financial stability of small and medium-sized enterprises (SMEs) in terms of the probability of future default. Objectives. The article aims to determine the most accurate model for predicting the probability of default of Russian SMEs, as well as develop a new model based on an up-to-date database of financial indicators obtained from open sources of information. Methods. For the study, we used logistic regression and analysis. Results. The article presents a developed six-factor logit model for estimating the probability of default a year before its occurrence, which has shown the highest accuracy of prediction in comparison with the models available in the literature. Relevance. The developed logit model may be of interest to a wide range of users wishing to invest in Russian SMEs due to its wide analytical base, high prediction accuracy, and ease of use and interpretation of results.