Designing an LSTM-Based Model for Financial Asset Forecasting Using Machine Learning

Yachou, Najlae; Abahman, Omar; Hakimi, Khalid

doi:10.2478/ceej-2026-0001

Abstract

This study examines the predictive performance of Long Short-Term Memory (LSTM) neural networks in forecasting stock prices, focusing on Apple Inc. (2010–2025) and comparing results with traditional models. The novelty lies in (1) dynamic training optimization using EarlyStopping and ReduceLROnPlateau, (2) a fully documented LSTM workflow with UML modeling for reproducibility, and (3), a 60-day forward iterative simulation. To assess generalizability, the same model was applied to Microsoft (MSFT) via transfer learning, confirming robust cross-asset performance.

Sensitivity analyses and stress tests during events such as COVID-19, highlight both the strengths and limitations. Using SHAP (SHapley Additive exPlanations), the study enhances interpretability by identifying key historical patterns that influence forecasts.

Results show high predictive accuracy (RMSE = 3.17, MAE = 2.61, R² = 0.9537, MAPE = 3.03%, SMAPE = 3.10%) and superior performance to ARIMA and SVR. Financial indicators, including hit ratio and Sharpe ratio above unity, confirm strong directional and risk-adjusted outcomes. The study underscores the growing relevance of AI-based forecasting compared with traditional econometric models (e.g., ARIMA, GARCH) in volatile markets and recommends incorporating sentiment or macroeconomic variables to enhance robustness. All code and workflows are publicly available on GitHub: https://github.com/najlae195/LSTM-Model.git.

References

Almahfouz, A. Kassem, N. & Moukalled, F. (2021). A Comparative Analysis of Econometric, Machine Learning and Deep Learning Models for Financial Time Series Forecasting. International Journal of Forecasting, 37(4), 1021–1035. https://doi.org/10.62951/ijamc.v1i2.71.
Search in Google Scholar Back to article
Aly, M., & Zhang, Y. (2024). Efficient Sequence Modeling in Cryptocurrency Forecasting Using GRU Networks. Journal of Financial Data Science, 6(1), 45–62.
Search in Google Scholar Back to article
Al-Selwi, S. M., Hassan, M. F., Abdulkadir, S. J., Muneer, A., Sumiea, E. H., Alqushaibi, A., & Ragab, M. G. (2024). RNN-LSTM: From Applications to Modeling Techniques and Beyond Systematic Review. Journal of King Saud University-Computer and Information Sciences, 12(5), 102068. https://doi.org/10.1016/j.jksuci.2024.102068.
Search in Google Scholar Back to article
Badar, M. I., et al. (2025). Enhanced Interpretable Forecasting of Cryptocurrency Prices Using Autoencoder Features and a Hybrid CNN–LSTM Model. Mathematics, 13(4), 678. https://doi.org/10.3390/math13121908.
Search in Google Scholar Back to article
Bao, W., Yue, J., & Rao, Y. (2017). A Deep Learning Framework for Financial Time Series Using Stacked Autoencoders and Long Short-Term Memory. PLOS ONE, 12(7): e0180944. https://doi.org/10.1371/journal.pone.0180944.
Search in Google Scholar Back to article
Bollerslev, T. (1986). Generalized Autoregressive Conditional Heteroskedasticity. Journal of Econometrics, 31(3), 307–327. https://doi.org/10.1016/0304-4076(86)90063-1.
Search in Google Scholar Back to article
Box, G.E.P., Jenkins, G.M., Reinsel, G.C., & Ljung, G.M. (2015). Time Series Analysis: Forecasting and Control (5th ed.). Wiley Series in Probability and Statistics. John Wiley & Sons, 65(4), 120–124. https://doi.org/10.1111/jtsa.12194.
Search in Google Scholar Back to article
Cheung, Y. W., & Lai, K. S. (1995). A Search for Long Memories in International Stock Market Returns. Journal of International Money and Finance, 14(4), 597615. https://doi.org/10.1016/0261-5606(95)93616-U.
Search in Google Scholar Back to article
Chlebus, M., Dyczko, M., & Wozniak, M. (2021). Nvidia’s Stock Returns Prediction Using Machine Learning Techniques for Time Series Forecasting Problems. Central European Economic Journal, 8(55). https://doi.org/10.2478/ceej-2021-0004.
Search in Google Scholar Back to article
Choi, W., Jang, S., Kim, S., Park, C., Park, S., & Song, S. (2024). Return Prediction by Machine Learning for the Korean Stock Market. Journal of the Korean Statistical Society, 53(1), 248–280. https://doi.org/10.1007/s42952-023-00245-0.
Search in Google Scholar Back to article
Choi, J. E., Shin, J. W., & Shin, D. W. (2025). Vector SHAP Values for Machine Learning Time Series Forecasting. Journal of Forecasting, Wiley, 44(3), 564–582. https://doi.org/10.1002/for.3220.
Search in Google Scholar Back to article
Chung, J., Gulcehre, C., Cho, K., & Bengio, Y. (2014). Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling. Computer Science > Neural and Evolutionary Computing. 45(6), 23–25. https://doi.org/10.48550/arXiv.1412.3555.
Search in Google Scholar Back to article
Cocco, L., Tonelli, R., & Marchesi, M. (2021). Predictions of Bitcoin Prices Through Machine Learning Based Frameworks. PeerJ Computer Science, 12(7), 413. https://doi.org/10.7717/peerj-cs.413.
Search in Google Scholar Back to article
Cont, R. (2001). Empirical Properties of Asset Returns: Stylized Facts and Statistical Issues. Quantitative Finance, 1(2), 223–236. https://doi.org/10.1080/713665670.
Search in Google Scholar Back to article
De Gooijer, J. G., & Hyndman, R. J. (2006). 25 Years of Time Series Forecasting. International Journal of Forecasting, 22(3), 443–473. https://doi.org/10.1016/j.ijforecast.2006.01.001.
Search in Google Scholar Back to article
Stempień, D., & Ślepaczuk, R. (2025). Hybrid Models for Financial Forecasting: Combining Econometric, Machine Learning, and Deep Learning Models. ARXIV, 2(4), 22–26. https://doi.org/10.48550/arXiv.2505.19617.
Search in Google Scholar Back to article
Engle, R. (2001). GARCH 101: The Use of ARCH/GARCH Models in Applied Econometrics. Journal of Economic Perspectives, 15(4), 157–168. https://doi.org/10.1257/jep.15.4.157.
Search in Google Scholar Back to article
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. https://doi.org/10.1016/j.ejor.2017.11.054.
Search in Google Scholar Back to article
Gers, F. A., Schmidhuber, J., & Cummins, F. (2000). Learning to Forget: Continual Prediction with LSTM. Neural Computation, 12(10), 2451–2471. https://doi.org/10.1162/089976600300015015.
Search in Google Scholar Back to article
Gers, F. A., Schraudolph, N. N., & Schmidhuber, J. (2002). Learning Precise Timing with LSTM Recurrent Networks. Journal of Machine Learning Research, 3(08), 115–143.
Search in Google Scholar Back to article
Idrees, M., Hussain Sial, M., & Ul Hassan, N. (2025). Forecasting Stock Prices Using LSTM with Attention. PLOS ONE, 20(1). https://doi.org/10.1371/journal.pone.e0271245.
Search in Google Scholar Back to article
He, K., Yang, Q., Ji, L., Pan, J., & Zou, Y. (2023). Financial Time Series Forecasting with the Deep Learning Ensemble Model (Mathematics). Multidisciplinary Digital Publishing Institute. 11(4), 1054. https://doi.org/10.3390/math11041054.
Search in Google Scholar Back to article
Jing, N., Wu, Z., & Wang, H. (2021). A Hybrid Model Integrating Deep Learning with Investor Sentiment Analysis for Stock Price Prediction. Expert Systems with Applications, 178, 115019. https://doi.org/10.1016/j.eswa.2021.115019.
Search in Google Scholar Back to article
Kehinde, T., Khan, W. A., & Chung, S. H. (2023). Financial Market Forecasting using RNN, LSTM, BiLSTM, GRU and Transformer-Based Deep Learning Algorithms.
Search in Google Scholar Back to article
Kobiela, D., Krefta, D., Król, W., & Weichbroth, P. (2022). ARIMA vs LSTM on NASDAQ Stock Exchange Data. Procedia Computer Science, 207(7), 3836–3845. https://doi.org/10.1016/j.procs.2022.09.445.
Search in Google Scholar Back to article
Lundberg, S. M., & Lee, S. I. (2017). A Unified Approach to Interpreting Model Predictions. Advances in Neural Information Processing Systems, 30(6), 4765–4774. https://doi.org/10.48550/arXiv.1705.07874.
Search in Google Scholar Back to article
Shen, S., Jiang, H., & Zhang, T. (2012). Stock Market Forecasting Using Machine Learning Algorithms. American Journal of Trade and Policy, 4(3),1–5. https://doi.org/10.18034/ajtp.v4i3.521.
Search in Google Scholar Back to article
Shi, Z., Hu, Y., Mo, G., & Wu, J. (2022). Attention-based CNN-LSTM and XGBoost hybrid model for stock prediction(arXiv:2204.02623). arXiv. https://doi.org/10.48550/ARXIV.2204.02623
Search in Google Scholar Back to article
Sima, Namini., & A, Namin. (2018). Forecasting Economics and Financial Time Series: ARIMA vs. LSTM. 122(10). https://doi.org/10.48550/arXiv.1803.06386.
Search in Google Scholar Back to article
Liu, J., Liu, Y., Ren, L., Li, X., & Wang, S. (2025). Trends and Trajectories: A Bibliometric Analysis of Financial Risk (2015–2024). International Journal of Financial Studies, 13(3), 132. https://doi.org/10.3390/ijfs13030132
Search in Google Scholar Back to article
Song, Z., Tsang, H. S.-H., Hsung, R. T.-C., Zhu, Y., & Lo, W.-L. (2025). Volatility and Value-at-Risk Forecasting Using BERT and Transformer Models Incorporating Investors‘ Textual Sentiments. Finance Research Letters, 85, 108210. https://doi.org/10.1016/j.frl.2025.108210.
Search in Google Scholar Back to article
Sun, W., & Li, X. (2025). Intraday and Post-Market Investor Sentiment for Stock Price Prediction: A Deep Learning Framework with Explainability and Quantitative Trading Strategy. Systems, 13(5), 390. https://doi.org/10.3390/systems13050390.
Search in Google Scholar Back to article
Tao, Z., Wu, W., & Wang, J. (2024). Series Decomposition Transformer with Period-Correlation for Stock Market Index Prediction. Expert Systems with Applications, 237, 121424. https://doi.org/10.1016/j.eswa.2023.121424
Search in Google Scholar Back to article
Taylor, S.J. (2008). Modelling Financial Time Series (2nd ed). Cambridge University Press. ISBN: 978-9812770844.
Search in Google Scholar Back to article
Yang, C., Zhai, J., & Tao, G. (2020). Deep Learning for Price Movement Prediction Using Convolutional Neural Networks and Long Short-Term Memory. Mathematical Problems in Engineering, 2020(1). https://doi.org/10.1155/2020/2746845.
Search in Google Scholar Back to article
Yang, A. (2025). Big Data-Driven Corporate Financial Forecasting and Decision Support: A Study of CNN-LSTM Machine Learning Models. Frontiers in Applied Mathematics and Statistics. 155(9), 24–28. https://doi.org/10.3389/fams.2025.1566078.
Search in Google Scholar Back to article
Zhang, G. P. (2003). Time Series Forecasting Using A Hybrid ARIMA and Neural Network Model. Neurocomputing, 50(4), 159–175. https://doi.org/10.1016/S0925-2312(01)00702-0.
Search in Google Scholar Back to article

Designing an LSTM-Based Model for Financial Asset Forecasting Using Machine Learning

Abstract

Paradigm

My account