A Study of Applying Intelligent Systems to the Warrant Pricing Model, Hedging Scheme, and Investment Strategy

• Main Authors: Wang Shen-Juh, 王勝助
• Other Authors: Dong-Her Shih
• Format: Others
• Language: zh-TW
• Published: 1999
• Online Access: http://ndltd.ncl.edu.tw/handle/89244375695094213034

碩士 === 國立雲林科技大學 === 資訊管理研究所 === 87 === Warrant is a type of call option. It provides people with multiple choice in speculate behavior contain arbitrage and hedging. In traditional option pricing model was a complex theory, and it had a lot of limitation and assumption that wait for overcome. This study tries to use artificial neural network to build option pricing model for warrant. In Black-Scholes pricing model, there was five variables impact the option price-- use to be the input variable in artificial neural network, both Back-Propagation Network (BPN) and Radial Basis Function Network (RBFN). Base on the difference analysis, it finds out another variable that can improve learning efficiency and effectivity. The reason why using NeuroFuzzy on warrant operation strategy and hedging position is that the hedging coefficient had fuzzy characteristic. There is, however, NeuroFuzzy tech can take a turn for disadvantage in Artificial Neural Network the better.