Financial Distress Prediction of K-means Clustering Based on Genetic Algorithm and Rough Set Theory
Hou, B.Z.
Download PDF

How to Cite

Hou B., 2016, Financial Distress Prediction of K-means Clustering Based on Genetic Algorithm and Rough Set Theory, Chemical Engineering Transactions, 51, 505-510.
Download PDF

Abstract

To the enterprise, the financial risks are impersonal. If there is no scientific method to predict and prevent financial risks, it is likely to cause the enterprise to fall into a difficult situation, even go bankrupt. In reality, the financial crisis of enterprises is expressed as a gradual deterioration of the financial indicators. Therefore, the financial crisis is symptomatic, and can be predicted. The main research direction of the current financial crisis early warning is to looking for a better model to help enterprises to find the financial crisis earlier. In view of the early warning of listed company’s financial crisis, this paper introduces the K clustering algorithm based on genetic algorithm; overcomes some problems of traditional K-means clustering, such as sensitive to the initial cluster center, easy to fall into the local optimal value; puts forward a new model which is K-means clustering model based on genetic algorithm. Then, we combine Rough set theory to evaluate financial position of the company comprehensively, and test the rationality of the model classification. Studies have shown that K- means clustering based on genetic algorithm can divide the company efficiently. The goodness of fit to evaluation results of rough set is up to 87.5%.
Download PDF