A Genetic Bankrupt Ratio Analysis Tool Using a Genetic Algorithm to Identify Influencing Financial Ratios

Financial ratios are key constituents of bankruptcy models. The bankruptcy prediction accuracy substantially improves when a limited number of ratios are used. From the literature, it has been found that human expertise has been applied to select financial ratios for bankruptcy models. Different experts tend to have different opinions and hence the bankruptcy prediction results depend upon their competency levels in that domain. Accordingly, there is a need for finding a systematic method or a tool to identify the influencing ratios. This paper develops a genetic bankrupt ratio analysis tool using a genetic algorithm to identify influencing ratios from different bankruptcy models and their influences in a quantitative form. The accuracy of values of influencing ratios is validated by comparing original threshold value of the bankruptcy models. The performance of influencing ratios has been compared with other feature selection techniques and the Altman model is considered to explain the effect of the influencing ratios.