Using non financial variables for business failure prediction : a multicriteria approach for the Belgian case

Business failure prediction is a topic of outmost importance for a lot of people. Consequently, many prediction models have been developed. Statistical and econometric procedures have been among the most widely used methods in this field. Most of these models developed in the past have been based solely on the use of financial ratios constructed from published accounting data, which are generally easy to obtain. In Belgium, however, corporate financial data are not always available. This situation clearly highlights the necessity of using non-financial information to predict bankruptcy. The objective of this study is to investigate the use and potentials of non-financial information such as whether financial statements were published by the firms or not, the delays in the publication of the annual financial statements, the existence of trial sentences, etc. In order to construct our model we use the UTADIS method and we compare the results with logistic regression and decision trees.