Corporate Financial Failure Prediction Model Using Multiple Discriminant Analysis

The prediction of corporate financial failure has been a crucial and challenging area, continuously extended since 1960 due to the highly importance for decision making of managers, investors and shareholders. Nowadays financial failure literature frames several bakruptcy prediction approaches based on financial and market information. Z-score model is one of the most frequently used model for early financial failure warning and considers various financial ratios selected as prediction variables. The purpose of this paper is to use multivariant discriminant analysis (MDA) to substantiate a score function effective in bankruptcy risk prediction of enterprises on Romanian economy example. In order to discriminate between bankrupt and non-bankrupt in the scoring model we used relevant financial ratios related to activity, liquidity, leverage and profitability. The weighting coefficients established between independent variables and the objective function-score, are determined by using statistical tools. In this context, the article aims to build a scoring function in order to identify bankrupt companies, using a sample of companies listed on Bucharest Stock Exchange. The results in this article can be used to appraise the effectiveness of applying MDA financial failure models for Romanian companies, to make an idea about curent and future financial situation, and take, if necessary, corrective measures.