{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T14:02:09Z","timestamp":1781618529796,"version":"3.54.5"},"reference-count":39,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["MAKE"],"abstract":"<jats:p>The integration of artificial intelligence (AI) and advanced deep learning techniques is reshaping intelligent financial forecasting and decision-support systems. This study presents a comprehensive comparative analysis of advanced deep learning models, including state-of-the-art transformer architectures and established non-transformer approaches, for long-term stock market index prediction. Utilizing historical data from major global indices (S&amp;P 500, NASDAQ, and Hang Seng), we evaluate ten models across multiple forecasting horizons. A dual-metric evaluation framework is employed, combining traditional predictive accuracy metrics with critical financial performance indicators such as returns, volatility, maximum drawdown, and the Sharpe ratio. Statistical validation through the Mann\u2013Whitney U test ensures robust differentiation in model performance. The results highlight that model effectiveness varies significantly with forecasting horizons and market conditions\u2014where transformer-based models like PatchTST excel in short-term forecasts, while simpler architectures demonstrate greater stability over extended periods. This research offers actionable insights for the development of AI-driven intelligent financial forecasting systems, enhancing risk-aware investment strategies and supporting practical applications in FinTech and smart financial analytics.<\/jats:p>","DOI":"10.3390\/make7030061","type":"journal-article","created":{"date-parts":[[2025,7,2]],"date-time":"2025-07-02T04:11:04Z","timestamp":1751429464000},"page":"61","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["AI-Driven Intelligent Financial Forecasting: A Comparative Study of Advanced Deep Learning Models for Long-Term Stock Market Prediction"],"prefix":"10.3390","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2880-6618","authenticated-orcid":false,"given":"Sira","family":"Yongchareon","sequence":"first","affiliation":[{"name":"School of Engineering, Computer and Mathematical Sciences, Auckland University of Technology, Auckland 1010, New Zealand"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,7,1]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1016\/j.eswa.2019.03.029","article-title":"CNNpred: CNN-based stock market prediction using a diverse set of variables","volume":"129","author":"Hoseinzade","year":"2019","journal-title":"Expert Syst. Appl."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1016\/j.ins.2003.03.023","article-title":"A hybrid genetic-neural architecture for stock indexes forecasting","volume":"170","author":"Armano","year":"2005","journal-title":"Inf. Sci."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"10696","DOI":"10.1016\/j.eswa.2009.02.043","article-title":"Forecasting stock market short-term trends using a neuro-fuzzy based methodology","volume":"36","author":"Atsalakis","year":"2009","journal-title":"Expert Syst. Appl."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Kumbure, M.M., Lohrmann, C., Luukka, P., and Porras, J. (2022). Machine learning techniques and data for stock market forecasting: A literature review. Expert Syst. Appl., 197.","DOI":"10.1016\/j.eswa.2022.116659"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Liu, L. (2022, January 11\u201312). Stock investment and trading strategy model based on autoregressive integrated moving average. Proceedings of the 2022 IEEE Conference on Telecommunications, Optics and Computer Science (TOCS), Virtually.","DOI":"10.1109\/TOCS56154.2022.10015924"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Jiang, W. (2021). Applications of deep learning in stock market prediction: Recent progress. Expert Syst. Appl., 184.","DOI":"10.1016\/j.eswa.2021.115537"},{"key":"ref_7","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., and Polosukhin, I. (2017, January 4\u20139). Attention is all you need. Proceedings of the 31st International Conference on Neural Information Processing Systems, Long Beach, CA, USA."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Wang, G., Liao, Y., Guo, L., Geng, J., and Ma, X. (2023, January 12\u201314). DLinear photovoltaic power generation forecasting based on reversible instance normalization. Proceedings of the 2023 IEEE 12th Data Driven Control and Learning Systems Conference (DDCLS), Xiangtan, China.","DOI":"10.1109\/DDCLS58216.2023.10166973"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Muhammad, T., Aftab, A.B., Ahsan, M., Muhu, M.M., Ibrahim, M., Khan, S.I., and Alam, M.S. (2022). Transformer-Based deep learning model for stock price prediction: A case study on Bangladesh stock market. arXiv.","DOI":"10.1142\/S146902682350013X"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Wang, C., Chen, Y., Zhang, S., and Zhang, Q. (2022). Stock market index prediction using deep transformer model. Expert Syst. Appl., 208.","DOI":"10.1016\/j.eswa.2022.118128"},{"key":"ref_11","first-page":"9881","article-title":"Non-stationary transformers: Exploring the stationarity in time series forecasting","volume":"35","author":"Liu","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_12","unstructured":"Wu, H., Hu, T., Liu, Y., Zhou, H., Wang, J., and Long, M. (2025, June 15). TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis. Available online: https:\/\/openreview.net\/pdf?id=ju_Uqw384Oq."},{"key":"ref_13","first-page":"22419","article-title":"Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting","volume":"34","author":"Wu","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Zhou, H., Zhang, S., Peng, J., Zhang, S., Li, J., Xiong, H., and Zhang, W. (2020, January 7\u201312). Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting. Proceedings of the AAAI Conference on Artificial Intelligence, New York, NY, USA.","DOI":"10.1609\/aaai.v35i12.17325"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Kim, J., Kim, H., Kim, H., Lee, D., and Yoon, S. (2025). A comprehensive survey of deep learning for time series forecasting: Architectural diversity and open challenges. Artif. Intell. Rev., 58.","DOI":"10.1007\/s10462-025-11223-9"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1007\/s10462-024-11044-2","article-title":"A systematic review for transformer-based long-term series forecasting","volume":"58","author":"Su","year":"2025","journal-title":"Artif. Intell. Rev."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"390","DOI":"10.1016\/j.ijforecast.2018.08.004","article-title":"Classification of intraday S&P500 returns with a Random Forest","volume":"35","author":"Lohrmann","year":"2019","journal-title":"Int. J. Forecast."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"927","DOI":"10.1016\/j.eswa.2005.06.024","article-title":"The use of data mining and neural networks for forecasting stock market returns","volume":"29","author":"Enke","year":"2005","journal-title":"Expert Syst. Appl."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"1071","DOI":"10.1007\/s11831-019-09344-w","article-title":"A survey of deep learning and its applications: A new paradigm to machine learning","volume":"27","author":"Dargan","year":"2020","journal-title":"Arch. Comput. Methods Eng."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"153","DOI":"10.1016\/j.eswa.2017.02.041","article-title":"Stock market one-day ahead movement prediction using disparate data sources","volume":"79","author":"Weng","year":"2017","journal-title":"Expert Syst. Appl."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1168","DOI":"10.1016\/j.procs.2020.03.049","article-title":"Stock market prediction using LSTM recurrent neural network","volume":"170","author":"Moghar","year":"2020","journal-title":"Procedia Comput. Sci."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Juairiah, F., Mahatabe, M., Jamal, H.B., Shiddika, A., Shawon, T.R., and Mandal, N.C. (2022, January 17\u201319). Stock price prediction: A time series analysis. Proceedings of the 2022 25th International Conference on Computer and Information Technology (ICCIT), Cox\u2019s Bazar, Bangladesh.","DOI":"10.1109\/ICCIT57492.2022.10056009"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Shah, J., Jain, R., Jolly, V., and Godbole, A. (2021, January 25\u201327). Stock market prediction using Bi- Directional LSTM. Proceedings of the 2021 International Conference on Communication information and Computing Technology (ICCICT), Mumbai, India.","DOI":"10.1109\/ICCICT50803.2021.9510147"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1016\/j.procs.2019.01.008","article-title":"Integration of principal component analysis and recurrent neural network to forecast the stock price of Casablanca stock exchange","volume":"148","author":"Berradi","year":"2019","journal-title":"Procedia Comput. Sci."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Eapen, J., Bein, D., and Verma, A. (2019, January 7\u20139). Novel deep learning model with CNN and Bi- Directional LSTM for improved stock market index prediction. Proceedings of the 2019 IEEE 9th Annual Computing and Communication Workshop and Conference (CCWC), Las Vegas, NV, USA.","DOI":"10.1109\/CCWC.2019.8666592"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Sethia, A., and Raut, P. (2019). Application of LSTM, GRU and ICA for stock price prediction. Information and Communication Technology for Intelligent Systems, Springer.","DOI":"10.1007\/978-981-13-1747-7_46"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Bhooshan, A., and Hari, V.S. (2021, January 12\u201313). Recurrent neural network estimator for stock price. Proceedings of the 2021 International Conference on Electrical, Communication, and Computer Engineering (ICECCE), Kuala Lumpur, Malaysia .","DOI":"10.1109\/ICECCE52056.2021.9514071"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Lu, W., Li, J., Li, Y., Sun, A., and Wang, J. (2020). A CNN-LSTM-Based model to forecast stock prices. Complexity, 2020.","DOI":"10.1155\/2020\/6622927"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Chen, Y., Fang, R., Liang, T., Sha, Z., Li, S., Yi, Y., Zhou, W., and Song, H. (2021). Stock price forecast based on CNN-BiLSTM-ECA model. Sci. Program., 2021.","DOI":"10.1155\/2021\/2446543"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"4741","DOI":"10.1007\/s00521-020-05532-z","article-title":"A CNN-BiLSTM-AM method for stock price prediction","volume":"33","author":"Lu","year":"2021","journal-title":"Neural Comput. Appl."},{"key":"ref_31","first-page":"876","article-title":"Predicting stock closing prices in emerging markets with transformer neural networks: The saudi stock exchange case","volume":"12","author":"Malibari","year":"2021","journal-title":"Int. J. Adv. Comput. Sci. Appl."},{"key":"ref_32","unstructured":"Zhang, Y., and Yan, J. (2022, January 25\u201329). Crossformer: Transformer utilizing cross-dimension dependency for multivariate time series forecasting. Proceedings of the Eleventh International Conference on Learning Representations, Virtual Event."},{"key":"ref_33","unstructured":"Nie, Y., Nguyen, N.H., Sinthong, P., and Kalagnanam, J. (2022). A time series is worth 64 words: Long-term forecasting with transformers. arXiv."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"3800","DOI":"10.1016\/j.egyr.2023.02.083","article-title":"A hybrid Autoformer framework for electricity demand forecasting","volume":"9","author":"Wang","year":"2023","journal-title":"Energy Rep."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Zhang, J., Ye, L., and Lai, Y. (2023). Stock price prediction using CNN-BiLSTM-Attention model. Mathematics, 11.","DOI":"10.3390\/math11091985"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Nagy, M., Valaskova, K., Kovalova, E., and Macura, M. (2024). Drivers of S&P 500\u2019s Profitability: Implications for Investment Strategy and Risk Management. Economies, 12.","DOI":"10.3390\/economies12040077"},{"key":"ref_37","first-page":"12677","article-title":"FiLM: Frequency improved Legendre memory model for long-term time series forecasting","volume":"35","author":"Zhou","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_38","unstructured":"Wang, H., Peng, J., Huang, F., Wang, J., Chen, J., and Xiao, Y. (2022, January 25\u201329). Micn: Multi-scale local and global context modeling for long-term series forecasting. Proceedings of the Eleventh International Conference on Learning Representations 2022, Virtual Event."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"79","DOI":"10.3354\/cr030079","article-title":"Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance","volume":"30","author":"Cort","year":"2005","journal-title":"Clim. Res."}],"container-title":["Machine Learning and Knowledge Extraction"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2504-4990\/7\/3\/61\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:02:41Z","timestamp":1760032961000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2504-4990\/7\/3\/61"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,1]]},"references-count":39,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2025,9]]}},"alternative-id":["make7030061"],"URL":"https:\/\/doi.org\/10.3390\/make7030061","relation":{},"ISSN":["2504-4990"],"issn-type":[{"value":"2504-4990","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,1]]}}}