股票市場的預測非常重要，因為成功的預測能帶來相當大的獲利。然而，能夠成功的預測是非常複雜而且困難的。 本研究擴展了適應性類神經模糊推論系統（ANFIS），創建一個交易決策支援系統，能夠利用模糊推論結合類神經網路的模型識別能力用於預測與交易台灣加權股價指數期貨。 本研究結果，提出了人工智能的方法結合模糊理論與類神經網絡來實現最佳化的交易規則。結果表明，結合模糊理論和類神經網絡產生的交易決策支援系統，能夠使交易員或是投資專家能夠克服眾多交易決策上資訊分析上的限制，提高投資效益，ANFIS能夠在預測未來的股市期貨指數上成為一個有用的工具，增加交易的獲利。 Stock market prediction is important because successful prediction of stock prices may promise attractive benefits. Yet, these tasks are highly complicated and very difficult. This thesis extends the Adaptive Neuro-Fuzzy Inference System (ANFIS), to create a trading decision support system that is capable of using fuzzy reasoning combined with the pattern recognition capability of neural networks to be used in forecasting and trading the futures of Taiwan Stock Exchange Capitalization Weighted Stock Index (TAIEX). This study, as a result, proposes an approach of artificial intelligence by integrating fuzzy theory with neural networks to achieve the optimization of trading rules. The result indicates that integrating fuzzy theory with neural networks has produced a trading decision support system which overcomes the physical limitations of human experts and traders in taking decisions of trading and improve the investment performance. The experimental results indicate that ANFIS can be a useful tool for economists and practitioners dealing with the forecasting of the stock index future price and increase the returns of a trader''s portfolio.