本研究主旨在透過結合長短期記憶（Long Short-Term Memory, LSTM）模型與模糊邏輯系統(Fuzzy Logic System)，提升股價預測之準確性與穩定性。以三種不同價位的股票台灣鴻海精密工業股份有限公司（股票代號：2317.TW）；台灣積體電路製造股份有限公司（股票代號：2330.TW）；陽明海運股份有限公司（股票代號：2609.TW）之歷史股價作為研究範例，建立雙層 LSTM 模型，並於預測誤差上導入高斯隸屬函數(Gaussian Membership Function)與三角形隸屬函數(Triangular Membership Function)所構成之模糊邏輯系統進行誤差修正。實驗結果顯示，融合模糊邏輯的 LSTM 模型在多次隨機預測中，其平均均方根誤差（Root Mean Square Error, RMSE）明顯低於單純使用 LSTM 的模型。該混合模型展現出更佳的預測穩定性，並提供更具彈性與可解釋性的預測結果。本研究顯示深度學習與模糊邏輯結合的潛力，未來可進一步應用於多種金融預測場景，以提升預測的準確度與模型透明度。

This study aims to enhance the accuracy and stability of stock price prediction by integrating the Long Short-Term Memory (LSTM) model with a Fuzzy Logic System (FLS). Historical stock price data from three Taiwanese companies with varying price levels—Hon Hai Precision Industry Co., Ltd. (2317.TW), Taiwan Semiconductor Manufacturing Company Limited (2330.TW), and Yang Ming Marine Transport Corporation (2609.TW)—are used as case studies. A two-layer LSTM model is constructed, and a fuzzy logic correction mechanism based on Gaussian and triangular membership functions is applied to adjust the prediction errors. Experimental results show that the LSTM model integrated with fuzzy logic consistently achieves lower average Root Mean Square Error (RMSE) across multiple randomized prediction trials compared to the standalone LSTM model. The proposed hybrid model demonstrates superior forecasting stability and provides more flexible and interpretable results. This study highlights the potential of combining deep learning with fuzzy logic systems and suggests future applications in various financial forecasting scenarios to improve predictive accuracy and model transparency.

• Chen, S.-M., & Lee, L.-C. (2010). Fuzzy time-series models for forecasting enrolments. Applied Soft Computing, 10(4), 1497–1504.
• Cho, K., Van Merriënboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y. (2014). Learning phrase representations using RNN encoder–decoder for statistical machine translation. Proceedings of EMNLP 2014, 1724–1734.
• Fischer, T., & Krauss, C. (2018). Deep learning with long short term memory networks for financial market predictions. European Journal of Operational Research, 270(2), 654–669.
• Gers, F. A., & Schmidhuber, J. (2000). Recurrent nets that time and count. Proceedings of the IJCNN, 189–194.
• Greff, K., Srivastava, R. K., Koutník, J., Steunebrink, B. R., & Schmidhuber, J. (2017). LSTM: A search space odyssey. IEEE Transactions on Neural Networks and Learning Systems, 28(10), 2222–2232.
• Gulmez, A., Erdem, H., & Yilmaz, E. (2023). GA-attention-fuzzy-stock-net: Hybrid deep fuzzy system for intraday trading. Neurocomputing, 515, 310–324.
• Hochreiter, S., & Schmidhuber, J. (1997). Long short‑term memory. Neural Computation, 9(8), 1735–1780.
• Huang, P., Chen, T., & Kuo, Y. (2024). Gaussian versus triangular fuzzy post-compensation on deep neural stock predictors. Expert Systems with Applications (in press).
• Klir, G. J., & Yuan, B. (1995). Fuzzy sets and fuzzy logic: Theory and applications. Prentice Hall.
• Mamdani, E. H., & Assilian, S. (1975). An experiment in linguistic synthesis with a fuzzy logic controller. International Journal of Man‑Machine Studies, 7(1), 1–13.
• Merity, S., Keskar, N. S., & Socher, R. (2018). Regularizing and optimizing LSTM language models. ICLR.
• Porru, S., Pinna, A., & Marchesi, M. (2018). A fuzzy-rule-based portfolio selection system with dynamic risk adjustment. Expert Systems with Applications, 104, 113–123.
• Ragab, A., Abdel-Aziz, M., & Ibrahim, H. (2024). Fuzzy BiLSTM with improved CPSO for cryptocurrency volatility forecasting. Applied Soft Computing, 146, 111226.
• Ross, T. J. (2010). Fuzzy logic with engineering applications (3rd ed.). Wiley.
• Sutskever, I., Vinyals, O., & Le, Q. V. (2014). Sequence to sequence learning with neural networks. Advances in NIPS, 27, 3104–3112.
• Takagi, T., & Sugeno, M. (1985). Fuzzy identification of systems and its applications to modeling and control. IEEE Transactions on Systems, Man, and Cybernetics, 15(1), 116–132.
• Wang, W., Liu, F., & Zhang, J. (2021). Fuzzy inference-based LSTM for long-term wind speed forecasting. Renewable Energy, 179, 1184–1198.
• Zadeh, L. A. (1965). Fuzzy sets. Information and Control, 8(3), 338–353.
• Zadeh, L. A. (1975). The concept of a linguistic variable and its application to approximate reasoning—I. Information Sciences, 8(3), 199–249.