Early Warning Model of Lower-stream Electronic Industry in Taiwan

• Main Authors: Chih-cheng Tuan, 段志成
• Other Authors: Ming-hsiang, Huang
• Format: Others
• Language: zh-TW
• Published: 2012
• Online Access: http://ndltd.ncl.edu.tw/handle/79219076063415732222

碩士 === 國立彰化師範大學 === 企業管理學系國際企業經營管理 === 100 === The performance of company is reflected on the financial statements periodically, but outsiders can not perceive a financial crisis until the underlying financial problem is disclosed. In fact, a financial crisis take times to happen and hence can be traced by certain signs. Thus, a proper risk prediction model can help to diagnose a possible risk in advance. Therefore, a formulation of early warning model is an important issue for both academic an industry. The objective of this study is investigate whether GA-SVM is a propitiate early warning model for the lower-stream electronic industry in Taiwan. The study adopts the lower-stream electronic firms listed in TSE or OTC in Taiwan as sample, covering a period from 2006 to 2010. The sample firms consists of 14 hazard firms and 28 matched firms. The accuracy of GA-SVM is compared with which of traditional BPN model. Empirical result suggests that our alternative approach outperforms the traditional BPN approach in terms of both prediction accuracy and prediction errors, RMSE.