Scopus

Evaluating the Predictive Performance of LSTM and Bi-LSTM Models in Financial Time Series Forecasting

Năm XB 2026 Tạp chí / Hội thảo Advances in Information and Communication Technology: Proceedings of the 4th International Conference, ICTA 2025, Volume 1 Volume 1, pp. 465-474 Đơn vị ICTU DOI / Link https://link.springer.com/chapter/10.1007/978-3-032-18316-3_51 ↗

Tác giả

Do Dinh Cuong

Tóm tắt

In the domain of financial time series forecasting, deep learning architectures have demonstrated significant efficacy in modeling intricate temporal dependencies. This study presents a comparative analysis of two prominent recurrent neural network frameworks-Long ShortTerm Memory (LSTM) and Bidirectional LSTM (Bi-LSTM) - with a specific focus on their predictive accuracy as quantified by the Mean Absolute Percentage Error (MAPE). Using historical stock price data of Apple Inc. (AAPL) obtained from Yahoo Finance, both models are trained and evaluated under identical experimental conditions. The empirical findings reveal that the Bi-LSTM architecture exhibits superior generalization capability, achieving a MAPE of \$\$2.4\\ % \\\$\$2.4%on the training set and \$\$2.1\\ % \\\$\$2.1%on the testing set. In contrast, the traditional LSTM model records higher MAPE values of \$\$4.79\\ % \\\$\$4.79%and \$\$3.9\\ % \\\$\$3.9%, respectively. These results underscore the enhanced predictive robustness of Bi-LSTM, affirming its advantage in capturing bidirectional temporal dynamics. Consequently, the Bi-LSTM model emerges as a more reliable computational tool for stock price forecasting, offering improved accuracy in support of data-driven financial decision-making.

Tài liệu tham khảo

[1] Financial Times. Us markets dominate global capitalization in 2025. Financial Times (2025). Accessed 04 May 2025

[2] Muhammad, D., Ahmed, I., Naveed, K., Bendechache, M.: An explainable deep learning approach for stock market trend prediction. Heliyon 10(21) (2024)

[3] Sharma, M.: Top 10 largest stock exchanges globally by market cap; India at 5th, April 2024. Accessed 04 May 2025

[4] Zou, J., et al.: Stock market prediction via deep learning techniques: a survey. arXiv preprint arXiv:2212.12717 (2022)

[5] Sezer, O., Gudelek, M.U., Ozbayoglu, A.M.: Deep learning models for price forecasting of financial time series: a survey. Wiley Interdisc. Rev. Data Mining Knowl. Discov. 10(2), e1519 (2020)

[6] Dhanapal, M.: Time-series forecasting with deep learning and stochastic models for probabilistic prediction in financial markets. SSRN Electron. J. (2025)

[7] Karim, M.E., Foysal, M., Das, S.: Stock price prediction using Bi-LSTM and GRU-based hybrid deep learning approach. In: Proceedings of Third Doctoral Symposium on Computational Intelligence: DoSCI 2022, pp. 701–711. Springer (2022)

[8] Shah, J., Jain, R., Jolly, V., Godbole, A.: Stock market prediction using bi-directional LSTM. In: 2021 International Conference on Communication Information and Computing Technology (ICCICT), pp. 1–5. IEEE (2021)

[9] Zhang, J., Ye, L., Lai, Y.: Stock price prediction using cnn-bilstmattention model. Mathematics 11(9), 1985 (2023)

[10] Baihaqi, T., Sugiyarto, M.A., Daksa, R.P., Kurniadi, F.I., Fakhruddin, M., Erandi, H.: Unveling the precision of deep learning models for stock price prediction: a comparative analysis of BiLSTM, LSTM, and GRU. In: 2023 International Conference on Converging Technology in Electrical and Information Engineering (ICCTEIE), pp. 61–64. IEEE (2023)

[11] Rath, S., Das, N.R., Pattanayak, B.K.: Stacked Bi-LSTM and e-optimized CNN-a hybrid deep learning model for stock price prediction. Opt. Mem. Neural Netw. 33(2), 102–120 (2024)

[12] Srilakshmi, K., Sruthi, C.S.: Prediction of TCS stock prices using deep learning models. In: 2021 7th International Conference on Advanced Computing and Communication Systems (ICACCS), vol. 1, pp. 1448–1455. IEEE (2021)

[13] Wang, S.: Stock market prediction based on BiLSTM. In: Proceedings of the 2nd International Conference on Artificial Intelligence, Database and Machine Learning (AIDML 2024), vol. 5 (2024)

[14] Du, N.: Research on apple's stock price trend forecasting. Highlights Sci. Eng. Technol. 92, 46–64 (2024)

Ghi chú

Source ID: 223; Author classification: ICTU - Main Author; First listed author: Dinh-Cuong Do; Contact author: Tran Quang Quy; Total authors: 4; Springer matched from provided ICTA 2025 volumes

← Quay lại danh sách bài báo