臺灣股價指數期貨套利之研究——類神經網路與灰色理論之應用

An Application of Neural Network and Grey Theory on Taiwan Stock Index Futures Arbitrage

本研究探討如何利用預測模型提高台股指數期貨之套利報酬。在套利過程中，決定獲利程度多寡的最大因素就是套利與平倉時機的選取，研究中比較台股指數期貨在：（1）不使用預測工具（2）使用類神經網路與（3）使用灰色馬可夫模型MarkvoGM (1，1) 對指數期貨之錯誤定價進行預測時的套利績效。研究結果顯示，在無套利區間為0.0148~-0.0146時，無論是在總報酬率或是平均報酬率方面，使用灰色馬可夫模型套利之績效最高，類神經網路次之，不使用預測方法最低。

This paper investigated how to use prediction models to obtain higher arbitrage returns on Taiwan Stock Index Futures. The selection of arbitrage and exercise timing significant1y influences the arbitrage performance and profits. The study examined Taiwan Stock Index Futures by utilizing: (1) absence of prediction models, (2) Neural Network, and (3) Markov GM (l,1) to arbitrage against the prediction of mis-pricing. Empirical results indicate that when no arbitrage boundaries ranged from 0.0148 to -0.0146, the Grey theory showed the best performance of arbitrage, neural network the next, and the absence of prediction models the worse.