Font Size: 

Corporate bankruptcies are an integral part of the functioning of economies. Statistical learning methods are increasingly used in the prediction of corporate bankruptcy. However, there is the problem of choosing an approach, method, procedure or algorithm that would be the most effective from a forecasting point of view. The purpose of the paper is to present the results of the application of statistical learning methods for corporate bankruptcy prediction. The research question was formulated: whether the use of semi-supervised statistical learning methods can improve the effectiveness of corporate bankruptcy prediction. The study used financial data of industrial processing enterprises operating in Poland. Corporate bankruptcy was predicted one, two and three years in advance. Selected methods of unsupervised, supervised and semi-supervised statistical learning were applied.