近年來，選擇權價格預測已成為財務領域的熱門研究議題，選擇權價格會被多項因素所影響，例如：標的證券的價格、選擇權的履約價格等因素。最近雖然有許多學者專家提出預測選擇權價格的方法，但是精準地預測選擇權的價格仍然是一個具有挑戰性的研究議題。
本研究提出一個結合模糊時間序列與類神經網路的新方法，預測選擇權的價格。首先，建立選擇權歷史收盤價格的模糊邏輯關係資料庫；接著利用模糊時間序列，自模糊邏輯關係資料庫中，選取數條與所欲預測當日的模糊邏輯關係最相近的模糊邏輯關係為訓練資料；最後以此訓練資料，利用類神經網路建立一個預測模型，預測當日選擇權的價格。本研究選用「臺灣證券交易所股價指數選擇權」的每日收盤價格為預測標的，比較本方法與其它方法的預測準確性。
實驗結果顯示，本方法於價內（in-the-money）選擇權的預測上，其準確性與GARCH, GJR, Grey-GJR, EGARCH和Grey-EGARCH相近，在價平（at-the-money）及價外（out-of-the-money）選擇權的預測上，本方法的預測準確度皆優於其他方法。所以，本研究成果可提供投資大眾作為投資選擇權的決策參考。

Recently, option price forecasting has become a popular financial issue. Clearly, option price is affected by many factors, such as the current underlying asset price, the strike price of the option. Though many researchers have proposed forecasting methods for option price, exact forecasting of the option price remains a challenging research issue.
In this study, we proposed a new method to forecast the prices of “Taiwan Stock Exchange Stock Price Index Options”. The new method, termed as fuzzy time series-based neural network approach (FTSBNN), is a hybrid method composed of a fuzzy time series model and a neural network model. The fuzzy time series model is a two factors high order fuzzy time series model. The first factor of this model is the closing price of “Taiwan Stock Exchange Stock Price Index Option” and the second factor is the index of “Taiwan Stock Exchange Index”. In the fuzzy time series model, we construct a Fuzzy Logic Relationships (FLRs) database of the historical option prices and the stock prices. We then use Euclidean distance as a screening mechanism to select several FLRs, from the FLR database, which are similar to the FLR of the predicting day. Finally, we use the selected FLRs as the training data set and use the neural network to construct a prediction model to predict the option price.
We compare the performance of FTSBNN with the existing methods, including GARCH, GJR, Grey-GJR, EGARCH and Grey-EGARCH. The results show that, for the in-the-money options, FTSBNN provides a similar accuracy as those of the existing methods. For the at-the-money options and the out-of-the-money options, FTSBNN provides higher accuracy in prediction than those of the existing methods.

1. Black, F., & Scholes, M. (1973). The Pricing of Options and corporate Liabilities. Journal of Finance, 637-654.
2. Chen, S. M. (1996). Forecasting Enrollments Based on Fuzzy Time Series. Fuzzy Sets and Systems, 81(3), 311-319.
3. Chen, S. M. (2002). Forecasting Enrollments Based on High-Order Fuzzy Time Series. Cybernetics and Systems: An International Journal, 33(1), 1-16.
4. Grudnitski, B., & Osburn, L. (1993). Forecasting S&P and Gold Futures Prices: An Application of Neural Network. Journal of Futures Markets, 13, 631-643.
5. Hamid, S. A., & Iqbal, Z. (2004). Using Neural Networks for Forecasting Volatility of S&P 500 Index Futures Prices. Journal of Business Research, 57, 1116-1125.
6. Hanke, M. (1999). Neural networks vs. Black-Scholes: An Empirical comparison of The Pricing Accuracy of Two Fundamentally Different Option Pricing Methods. Journal of Computational Intelligence in Finance, 26-34.
7. Huarng, K. (1996). Effective Lengths of Intervals to Improve Forecasting in Fuzzy Time Series. Fuzzy Sets and Systems, 81(3), 311-319.
8. Hutchinson, J., Lo, A., & Poggio, T. (1994). A Nonparametric Approach to Pricing and Hedging Derivative Structure via Learning Networks. Journal of Finance, 49, 851-889.
9. Ko, P. C. (2009). Option valuation base on the neural regression model. Expert Systems with Applications, 36(1), 464-471.
10. Lajbcygier, P., Boek, C., Flitman, A., & Palaniswami, M. (1996). Comparing conventional and Artificial Neural Network Models for the Pricing of Options on Futures. Neuro of Journal, 4, 16-24.
11. Lee, L. W., Chen, S. M., & Leu, Y. H. (2004). A New Method for Handling Forecasting Problems Based on Two-Factors High-Order Fuzzy Time series. Proceedings of the 2004 Ninth Conference on Artificial Intelligence and Applications, Taipei, Taiwan, Republic of China, November 2004.
12. Lee, L. W., Wang, L. H., Chen, S. M., & Leu, Y. H. (2006). Handling forecasting problems based on two-factors high-order fuzzy time series. IEEE Transactions on Fuzzy Systems, 14(3), 468–477. 
13. Leu, Y. H., Lee, C. P., & Jou, Y. Z. (2009). A distance-based fuzzy time series model for exchange rates forecasting. Expert Systems with Applications, 36(4), 8107-8114.
14. Malliaris, M., & Salchenberger, L. (1996). Using Neural Networks to Forecast the S&P 100 Implied Volatility. Neuro computing, 10(2), 183-195.
15. Montagna, G., Morelli, M., Nicrosini, O., Amato, P., & Farina, M. (2003). Pricing Derivatives by Path Integral and Neural Networks. Physica A, 324, 189-195.
16. Morelli, M. J., Montagna, G., Nicrosini, O., Treccani, M., & Farina, M. (2004). Pricing Financial Derivatives with Neural Networks. Physica A, 338, 160-165.
17. Song, Q., & Chissom, B. S. (1993). Forecasting Enrollments with Fuzzy Time Series-Part Ι. Fuzzy Sets and Systems, 54(1), 1-9.
18. Song, Q., & Chissom, B. S. (1993). Fuzzy Time Series and Its Models. Fuzzy Sets and Systems, 54(3), 269-277.
19. Song, Q., & Chissom, B. S. (1994). Forecasting Enrollments with Fuzzy Time Series- Part II. Fuzzy Sets and Systems, 62(1), 1-8.
20. Tseng, C. H., Cheng, S. T., Wang, Y. H., & Peng, J. T. (2008). Artificial neural network model of the hybrid EGARCH volatility of the Taiwan stock index option prices. Physica A, 387, 3192-3200.
21. Wang, Y. H. (2009). Nonlinear neural network forecasting model for stock index option price: Hybrid GJR–GARCH approach. Expert Systems with Applications, 36, 564-570.
22. White, H. (1989). Some Asymptotic Results for Learning in Single Hidden-Layer Feedforward Network Models. Journal of the American Statistical Association.
23. Yu, H. K. (2005). Weighted fuzzy time series models for TAIEX forecasting. Physica A: Statistical Mechanics and its Applications, 349(3-4), 609-624.
24. Zadeh, L. A. (1965). Fuzzy sets. Information Control, 8, 338-353.
25. 文德蘭（1999），利用類神經網路在臺灣認購權證評價模式錯價之探討，政治大學，臺北。
26. 王國軒（2003），運用不同類神經網路與模糊理論評價認購權證比較之研究，臺北大學，臺北。 
27. 呂正東（2003），模糊三項式樹狀選擇權評價模型，大同大學，臺北。
28. 李沃牆（1998），計算智慧在選擇權定價上的發展－人工神經網路、遺傳規劃、遺傳演算法，政治大學，臺北。
29. 李建信（2003），「臺指選擇權之評價－ANN 與GANN 模型之績效比較」，真理財經學報，第八期，頁25-50。
30. 李惠如（2003），類神經網絡於臺灣股市認購權證訂價之實證研究，臺北大學，臺北。
31. 周育如（2007），使用加權模糊時間序列預測匯率，碩士論文，臺灣科技大學，臺北。
32. 林宜芬（2006），遺傳程式規劃為基的時間序列模型在金融市場之應用，輔仁大學，臺北。
33. 林詠智（2007），應用遺傳演化類神經網路模型建立衍生性金融商品投資策略之研究，臺北大學，臺北。
34. 林聖哲（2002），不同人工智慧演算方法於認購權證評價績效之研究，實踐大學，臺北。
35. 林鈺芳（2005），以類神經網路進行雙變量模糊時間序列股價預測，逢甲大學，臺中。
 
36. 施東河、王勝助（2001），「認購權證評價模式與避險部位之研究－混合式智慧型系統的應用」，資訊管理學報，第七卷，第二期，頁123-142。
37. 柯淑玲（2000），運用類神經網路於臺股認購權證評價模式之實證研究，義守大學，高雄。
38. 張克群（2005），運用計算智慧演算法於股票選擇權評價與套利之研究，真理大學，臺北。
39. 許嘉元（1993），時間數列的模糊分析和預測，政治大學，臺北。
40. 郭伯聖（2002），臺灣股市認購權證定價模型之實證研究－ANN-GARCH模型之應用，臺北大學，臺北。
41. 陳安斌、張志良（2000），「運用類神經網路在選擇權評價及避險之研究」，Mar. 2000，中華管理評論，頁43-57。
42. 陳怡和（1997），運用類神經網路在外匯選擇權評價模式之實證研究，交通大學，新竹。
43. 陳威光（2001），衍生性金融商品－選擇權、期貨與交換，臺北，智勝。
44. 陳彥廷（2008），分析與預測波羅的海運價指數波動之趨勢－應用模糊時間序列法，交通大學，新竹。
 
45. 黃鐘億（2008），以改良式倒傳遞類神經網路運用成分股與技術指標預測臺灣50指數報酬率之研究，臺北大學，臺北。
46. 葉怡成（2002），類神經網路模式應用與實作，臺北，儒林。
47. 蔡馥璟（2005），時間序列法於警力資源規劃之研究，成功大學，臺南。
48. 薛淑嫻（1999），認購權證評價模型之研究－基因演算法與類神經網路之應用，銘傳大學，臺北。