Hybrid genetic algorithm and fuzzy clustering for bankruptcy prediction
tIn the design of a financial bankruptcy prediction model, financial ratio selection and classifier designplay major roles. Methodology based on expert opinion, statistical theory and computational intelli-gence technique has been widely applied. In this study, a hybrid structure integrating statistical theoryand computational intelligence technique was developed using genetic algorithm (GA) with statisticalmeasurements and fuzzy logic based fitness functions for key ratio selection. A fuzzy clustering algorithmwas used for the classifier design. In the experiments, two financial ratio sets, one extracted from thesuggestions of other studies and the other obtained by using the GA toolbox in the SAS statistical soft-ware package, were applied to examine the proposed ratio selection schemes. For classifier design, thedeveloped fuzzy classifier was compared with the well known BPNN classifier frequently used in otherstudies. Besides, comparison between the developed hybrid structure and other well applied structureswas also given. Experimental results based on one to four years of financial data prior to the occurrenceof bankruptcy were used to evaluate the performance of the proposed prediction model.
Keyword： Bankruptcy,Financial ratios Prediction model,Genetic algorithm,Fuzzy clusteringFitness function