Default Prediction for Housing and Utilities Management Firms Using Non-Financial Data
For many years financial ratios were used as predictors of default. However, biases in financial reporting of firms in Russia call the applicability of this approach into question. The alternative approach is to use non-financial data in such models.
The purpose of this paper is to discover, whether non-financial data, such as information, related to court trials, unplanned inspections and age of the firm can significantly improve the accuracy of default prediction in Housing and Utilities Management Services industry.
This part of the services sector is chosen as one of the riskiest industry, in which the default of the firm affects not only the conventional stakeholders, like banks, shareholders, employees etc, but also the clients.
A dataset of 378 Housing and Utilities Services Management firms, which faced a default, and 765 solvent “healthy peers” is used to create and test default prediction models. Logistic regression is used as the classification algorithm.
The results suggest that adding non-financial data can significantly improve the accuracy of default prediction, and, moreover, non-financial data can be used solely without any financial ratios to create classification models, which perform acceptable accuracy.
The paper contributes to the existing literature by new evidence of benefits of using non-financial data in default prediction models. Also, we were able to collect a unique dataset of unplanned inspections and use this data for default prediction, which seems to be the first case of this kind.