Applied Genetic Programming to Construct the Enterprise Distress Diagnosis Model

• Main Authors: Po-yi Cheng, 鄭柏翊
• Other Authors: Chih-Chou Chiu
• Format: Others
• Language: zh-TW
• Published: 2002
• Online Access: http://ndltd.ncl.edu.tw/handle/28513603039526661090

碩士 === 國立臺北科技大學 === 商業自動化與管理研究所 === 90 === In order to prevent the occurrence of financial distress, enterprises always establish a predictive model to help manager to make an appropriate decision. Basically, there are many different kind of reasons will cause the failure. But however, constructing a successful diagnostic model is not an easy task. The main reason for this incorrect judgment is the ignorance of some valuable indicators. Those that have witnessed a growth in ‘knowledge-based companies’, we have realized that the knowledge encompassed within the organization is a valuable asset, and its demise can represent a significant risk to the continued safe operation of the company. Intelligent capital represents intangible assets that frequently do not appear on the balance sheet. Today, to measure the assets of companies, it is very important to notice that IC’s value and strength tend to vary depending on the goals of the organization. The objective of this study is to explore the performance of enterprise distress diagnosis by two different algorithms-Genetic programming and classification and regression tree. The results show that (1) Financial indices have great explanation for predicting bankruptcy. (2) The intelligent capital indices are important in the enterprise distress diagnosis, especially in high-tech industry.