The Construction of Taiwan Automobile Material DamageInsurance Underwritting System-Application of Artificial Intelligences

• Main Authors: Rung-Guang Ding, 丁榮光
• Other Authors: Wo-Chiang Lee
• Format: Others
• Language: zh-TW
• Published: 2004
• Online Access: http://ndltd.ncl.edu.tw/handle/28t7st

碩士 === 銘傳大學 === 經濟學系碩士在職專班 === 92 === To the kinds of automobile insurance, the revenue of material damage insurance has always a high proportion. According to past researches,the premium of automobile material damage insurance is ten times of automobile third party liability insurance.On the other side,the change of automobile material damage insurance’s loss rate can affect the other automobile insurance.That is to say,whether the automobile material damage insurance can got profit or not will affect the business and performance of material insurance company. The study try to input the automobile material damage insurance’s underwriting data to the logit and ANN model to construct a underwriting system. Empirical study shows that the two models can obtain at least 80% correct rate whether in-sample data or out-sample.In the future,we can construct the underwriting system by the two models.