DOI:
https://doi.org/10.64539/sjcs.v2i2.2026.377Keywords:
Fuzzy Logic, Deep Learning, Stock Price Forecasting, Financial Time Series, Emerging Markets, XAIAbstract
Precise stock price forecasting is vital for economic stability and capital allocation, yet it remains a tenacious challenge in emerging economies due to the inherent uncertainty and non-linearity of financial time series. Despite advances in deep learning, existing models often lack linguistic interpretability, fail to adapt to rapid market shifts, or exhibit look-ahead bias due to static validation splits. Moreover, empirical research focused on African financial systems, such as the Nigerian market, remains sparse, limiting the practical utility of conventional black-box architectures. This study proposes a Hybrid Neuro-Fuzzy and Deep Learning (HNFDL) framework that integrates fuzzy inference systems with Long Short-Term Memory (LSTM) networks and Genetic Algorithms (GA). The objective is to unify semantic reasoning with temporal learning to improve forecasting accuracy while maintaining high model transparency through explainable AI (XAI). Empirical validation using data from the Nigerian Exchange Group (NGX) (Dangote Cement, Zenith Bank, and the NSE All-Share Index) shows that the HNFDL model achieved a directional accuracy of 68.4% and a Mean Absolute Percentage Error (MAPE) as low as 4.36%. An ablation study confirmed that GA-driven optimization reduced the Root Mean Square Error (RMSE) by 8.4%, while the Diebold-Mariano test () statistically confirmed the model's superiority over standalone LSTM and fuzzy baselines. These results demonstrate that combining explainable fuzzy reasoning with adaptive deep neural architectures significantly enhances decision-making confidence. The framework provides a robust, statistically validated decision-support tool for investors and policy makers operating within volatile, information-asymmetric financial environments.
References
[1] H. Wu, H. Long, J. Jiang, “Mixed-order fuzzy time series forecast,” Mathematics, vol. 13, no. 11, Art. no. 1705, 2025. https://doi.org/10.3390/math13111705.
[2] T. A. Akinwale, O. Rogundade, and A. F. Adekoya, “Translating Nigeria stock market prices using artificial neural networks for effective prediction,” Journal of Theoretical and Applied Information Technology, 2005. https://www.researchgate.net/publication/270285808.
[3] W. Sun et al, “Research on deep learning model for stock prediction by integrating frequency domain and time series features,” Scientific Reports, vol. 15, no. 1, Art. no. 30386, 2025. https://doi.org/10.1038/s41598-025-14872-6.
[4] A. K. Ojo and I. J. Okafor, “Forecasting Nigerian equity stock returns using long short-term memory technique,” Journal of Advances in Mathematics and Computer Science, vol. 39, no. 7, pp. 45–54, 2024. https://doi.org/10.9734/jamcs/2024/v39i71911.
[5] Z. Liu, “Forecasting stock prices based on multivariable fuzzy time series,” AIMS Mathematics, vol. 8, no. 6, pp. 12778–12792, 2023. https://doi.org/10.3934/math.2023643.
[6] H.-Y. Lin and B.-W. Hsu, “Application of hybrid fuzzy interval-based machine learning models on financial time series: A case study of the Taiwan biotech index during the epidemic period,” Frontiers in Artificial Intelligence, vol. 6, Art. no. 1283741, 2024. https://doi.org/10.3389/frai.2023.1283741.
[7] S. G. Hassan et al., “A novel first-order fuzzy rules-based forecasting system using distance measures approach for financial market forecasting,” Journal of Mathematics, vol. 2023, Art. no. 8027664, 2023. https://doi.org/10.1155/2023/8027664.
[8] K. Wang, “Multifactor prediction model for stock market analysis based on deep learning techniques,” Scientific Reports, vol. 15, no. 1, Art. no. 5121, 2025. https://doi.org/10.1038/s41598-025-88734-6.
[9] B. Gülmez, “GA-Attention-Fuzzy-Stock-Net: An optimized neuro-fuzzy system for stock market price prediction with genetic algorithm and attention mechanism,” Heliyon, vol. 11, no. 3, Art. no. e42393, 2025. https://doi.org/10.1016/j.heliyon.2025.e42393.
[10] J.-W. Wang and J.-S. Chen, “An integrated fuzzy convolutional neural network model for stock price prediction,” Engineering Proceedings, vol. 9, Art. no. 8003, pp. 1–8, 2025. https://doi.org/10.3390/engproc2025098003.
[11] S. Iqbal, “Advancing stock price index forecasting based on hybrid picture fuzzy time series model,” International Journal of Fuzzy Systems, 2025. https://doi.org/10.1007/s40815-025-02146-2.
[12] P. Li, H. Gu, L. Yin, and B. Li, “Research on trend prediction of component stocks in fuzzy time series based on deep forest,” CAAI Transactions on Intelligence Technology, vol. 7, no. 4, pp. 617–626, 2022. https://doi.org/10.1049/cit2.12139.
[13] A. Staffini, “Stock price forecasting by a deep convolutional generative adversarial network,” Frontiers in Artificial Intelligence, vol. 5, Art. no. 837596, 2022. https://doi.org/10.3389/frai.2022.837596.
[14] G. E. P. Box, G. M. Jenkins, G. C. Reinsel, and G. M. Ljung, Time Series Analysis: Forecasting and Control, 5th ed. Hoboken, NJ, USA: John Wiley & Sons, 2015. https://books.google.co.id/books?id=rNt5CgAAQBAJ.
[15] E. W. Taylor, “Critical reflection and transformative learning: A critical review,” PAACE Journal of Lifelong Learning, vol. 26, pp. 77–95, 2017.
[16] V. Chung, J. Espinoza, and R. Quispe, “Forecasting Financial Volatility Under Structural Breaks: A Comparative Study of GARCH Models and Deep Learning Techniques,” Journal of Risk and Financial Management, vol. 18, no. 9, https://doi.org/10.3390/jrfm18090494.
[17] P. H. Vuong et al., “A bibliometric literature review of stock price forecasting: From statistical model to deep learning approach,” Science Progress, vol. 107, no. 1, pp. 1–25, 2024. https://doi.org/10.1177/00368504241236557.
[18] A. Ijegwa, V. Rebecca, F. Olusegun, O. Isaac, “A Predictive Stock Market Technical Analysis Using Fuzzy Logic,” Computer and Information Science, vol. 7, no. 3, 2014. https://doi.org/10.5539/cis.v7n3p1.
[19] V. Vaidehi, S. Monica, S. M. S. Safeer, M. Deepika, and S. Sangeetha, “A prediction system based on fuzzy logic,” in Proc. World Congress on Engineering and Computer Science (WCECS 2008), pp. 804–809, 2008. https://www.iaeng.org/publication/WCECS2008/WCECS2008_pp804-809.pdf.
[20] R. M. Lincy and J. John, “A multiple fuzzy inference systems framework for daily stock trading with application to NASDAQ stock exchange,” Expert Systems with Applications, vol. 44, pp. 13–21, 2016. https://doi.org/10.1016/j.eswa.2015.08.045.
[21] D. I. Ajiga, R. A. Adeleye, T. S. Tubokirifuruar, B. G. Bello, and N. L. Ndubuisi, “Machine learning for stock market forecasting: A review of models and accuracy,” Finance & Accounting Research Journal, vol. 6, no. 2, pp. 112–124, 2024. https://doi.org/10.51594/farj.v6i2.783.
[22] C. Ayantse, O. S. Yaya, O. U. Joseph, and D. F. Arawomo, “Predicting Nigerian stock market returns based on daily business news headlines,” Science Journal of Applied Mathematics and Statistics, vol. 12, no. 6, pp. 90–98, 2024. https://doi.org/10.11648/j.sjams.20241206.11.
[23] M. Abhishek, V. Bhattacharjee, and P. S. Bishnu, “Stock price forecasting using fuzzy logic-enhanced deep learning models,” SSRN Electronic Journal, 2024. [Online]. Available: https://ssrn.com/abstract=5023575.
[24] J. Timko, R. El Shawi, and S. Tomasiello, “Optimizing stock price forecasting: A hybrid approach using fuzziness and automated machine learning,” Expert Systems with Applications, vol. 295, Art. no. 128844, 2025. https://doi.org/10.1016/j.eswa.2025.128844.
