A HYBRID MODEL FOR BUSINESS FAILURE PREDICTION – UTILIZATION OF PARTICLE SWARM OPTIMIZATION AND SUPPORT VECTOR MACHINES

Abstract

Bankruptcy has long been an important topic in flnance and account- ing research. Recent headline bankruptcies have included Enron, Fannie Mae, Freddie Mac, Washington Mutual, Merrill Lynch, and Lehman Brothers. These bankruptcies and their flnancial fallout have become a serious public concern due to huge in∞uence these companies play in the real economy. Many researchers be- gan investigating bankruptcy predictions back in the early 1970s. However, until recently, most research used prediction models based on traditional statistics. In recent years, however, newly-developed data mining techniques have been applied to various flelds, including performance prediction systems. This research applies particle swarm optimization (PSO) to obtain suitable parameter settings for a sup- port vector machine (SVM) model and to select a subset of beneflcial features without reducing the classiflcation accuracy rate. Experiments were conducted on an initial sample of 80 electronic companies listed on the Taiwan Stock Exchange Corporation (TSEC). This paper makes four critical contributions: (1) The results indicate the busi- ness cycle factor mainly afiects flnancial prediction performance and has a greater in∞uence than flnancial ratios. (2) The closer we get to the actual occurrence of flnancial distress, the higher the accuracy obtained both with and without fea- ture selection under the business cycle approach. For example, PSO-SVM without feature selection provides 89.37% average correct cross-validation for two quarters prior to the occurrence of flnancial distress. (3) Our empirical results show that PSO integrated with SVM provides better classiflcation accuracy than the Grid search, and genetic algorithm (GA) with SVM approaches for companies as normal or under threat. (4) The PSO-SVM model also provides better prediction accu- racy than do the Grid-SVM, GA-SVM, SVM, SOM, and SVR-SOM approaches for seven well-known UCI datasets. Therefore, this paper proposes that the PSO- SVM approach could be a more suitable method for predicting potential flnancial distress.