{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T20:31:54Z","timestamp":1782419514343,"version":"3.54.5"},"reference-count":40,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,6,4]],"date-time":"2025-06-04T00:00:00Z","timestamp":1748995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Appl. Math. Stat."],"abstract":"<jats:p>Stock price prediction plays a crucial role in investment, corporate strategic planning, and government policy formulation. However, stock price prediction remains a challenging issue. To tackle this issue, we propose a novel hybrid model, termed M-A-BiLSTM, which integrates Attention mechanisms, Multi-Layer Perceptron (MLP), and Bidirectional Long Short-Term Memory (Bi-LSTM). This model is designed to enhance feature selection capabilities and capture nonlinear patterns in financial time series. Evaluated on stock datasets from Apple, ExxonMobil, Tesla, and Snapchat, our model outperforms existing deep learning methods, achieving a 15.91% reduction in Mean Squared Error (MSE) for Tesla and a 5.95% increase in R-squared (<jats:italic>R<\/jats:italic><jats:sup>2<\/jats:sup>) for Apple. Meanwhile, the MSE on the ExxonMobil dataset decreased to 1.8954, showing a significant reduction, while the <jats:italic>R<\/jats:italic><jats:sup>2<\/jats:sup> increased to 0.9887. These results demonstrate the model's superior predictive power, offering a robust and interpretable approach for financial forecasting.<\/jats:p>","DOI":"10.3389\/fams.2025.1588202","type":"journal-article","created":{"date-parts":[[2025,6,4]],"date-time":"2025-06-04T05:40:02Z","timestamp":1749015602000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Improving stock price forecasting with M-A-BiLSTM: a novel approach"],"prefix":"10.3389","volume":"11","author":[{"given":"Zihan","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,6,4]]},"reference":[{"key":"B1","first-page":"81","article-title":"Factors affecting the market stock price-The case of the insurance companies listed in Amman Stock Exchange","volume":"7","author":"Al Qaisi","year":"2016","journal-title":"Int J Bus Soc Sci"},{"key":"B2","doi-asserted-by":"publisher","first-page":"100190","DOI":"10.1016\/j.cosrev.2019.08.001","article-title":"Systematic analysis and review of stock market prediction techniques","volume":"34","author":"Gandhmal","year":"2019","journal-title":"Comput Sci Rev"},{"key":"B3","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1007\/s10844-023-00804-1","article-title":"Stock market prediction with time series data and news headlines: a stacking ensemble approach","volume":"62","author":"Corizzo","year":"2024","journal-title":"J Intell Inf Syst"},{"key":"B4","first-page":"2013","article-title":"Using neural networks to forecast stock market prices","volume":"333","author":"Lawrence","year":"1997","journal-title":"Univ Manitoba"},{"key":"B5","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1016\/S0957-4174(00)00027-0","article-title":"Genetic algorithms approach to feature discretization in artificial neural networks for the prediction of stock price index","volume":"19","author":"Kim","year":"2000","journal-title":"Expert Syst Applic"},{"key":"B6","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/EICT48899.2019.9068850","article-title":"Stock price prediction: a comparative study between traditional statistical approach and machine learning approach","volume-title":"2019 4th International Conference on Electrical Information and Communication Technology (EICT)","author":"Bhattacharjee","year":"2019"},{"key":"B7","doi-asserted-by":"publisher","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 Applic"},{"key":"B8","article-title":"Prediction of stock performance by using logistic regression model: evidence from Pakistan Stock Exchange (PSX)","author":"Ali","year":"2018","journal-title":"Patron of the Conference"},{"key":"B9","doi-asserted-by":"publisher","first-page":"4055281","DOI":"10.1155\/2021\/4055281","article-title":"Stock prediction based on optimized LSTM and GRU models","volume":"2021","author":"Gao","year":"2021","journal-title":"Sci Program"},{"key":"B10","first-page":"1","article-title":"Predicting stock market trends using LSTM networks: overcoming RNN limitations for improved financial forecasting","volume":"4","author":"Wang","year":"2024","journal-title":"J Comput Sci Softw Applic"},{"key":"B11","doi-asserted-by":"crossref","first-page":"3285","DOI":"10.1109\/BigData47090.2019.9005997","article-title":"The performance of LSTM and BiLSTM in forecasting time series","volume-title":"2019 IEEE International conference on big data (Big Data)","author":"Siami-Namini","year":"2019"},{"key":"B12","doi-asserted-by":"publisher","first-page":"281","DOI":"10.1177\/01445987241269496","article-title":"Comparative study of long short-term memory (LSTM), bidirectional LSTM, and traditional machine learning approaches for energy consumption prediction","volume":"43","author":"Alizadegan","year":"2025","journal-title":"Energy Explor Exploit"},{"key":"B13","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1016\/j.neucom.2021.03.091","article-title":"review on the attention mechanism of deep learning","volume":"452","author":"Niu","year":"2021","journal-title":"Neurocomputing"},{"key":"B14","doi-asserted-by":"publisher","first-page":"012029","DOI":"10.1088\/1742-6596\/1994\/1\/012029","article-title":"A Deep Neural Network for Stock Price Prediction","author":"Dai","year":"2021","journal-title":"Journal of Physics: Conference Series"},{"key":"B15","doi-asserted-by":"publisher","first-page":"135","DOI":"10.21660\/2024.119.m2415","article-title":"Advanced earthquake prediction: unifying networks, algorithms, and attention-driven lstm modelling","volume":"27","author":"Rusho","year":"2024","journal-title":"GEOMATE J"},{"key":"B16","doi-asserted-by":"publisher","first-page":"111290","DOI":"10.1016\/j.knosys.2023.111290","article-title":"Deep LSTM and LSTM-Attention Q-learning based reinforcement learning in oil and gas sector prediction","volume":"284","author":"Oyewola","year":"2024","journal-title":"Knowl-Based Syst"},{"key":"B17","doi-asserted-by":"publisher","first-page":"373","DOI":"10.1007\/s00181-024-02644-6","article-title":"Enhancing stock price prediction using GANs and transformer-based attention mechanisms","volume":"68","author":"Li","year":"2025","journal-title":"Empir Econ"},{"key":"B18","first-page":"13","article-title":"Forecasting gold prices with MLP neural networks: a machine learning approach","volume":"13","author":"Tashakkori","year":"2024","journal-title":"Int J Sci Eng Applic"},{"key":"B19","article-title":"Tsmixer: an all-mlp architecture for time series forecasting","author":"Chen","year":"2023","journal-title":"arXiv preprint arXiv:230306053"},{"key":"B20","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1007\/978-981-16-7597-3_7","article-title":"Performance analysis of deep neural network models for weather forecasting in Bangladesh","volume-title":"Proceedings of the Third International Conference on Trends in Computational and Cognitive Engineering: TCCE 2021","author":"Badal","year":"2022"},{"key":"B21","doi-asserted-by":"publisher","first-page":"101179","DOI":"10.1016\/j.measen.2024.101179","article-title":"Advanced fusion of MTM-LSTM and MLP models for time series forecasting: an application for forecasting the solar radiation","volume":"33","author":"Mohammadi","year":"2024","journal-title":"Measur Sensors"},{"key":"B22","doi-asserted-by":"publisher","first-page":"7705","DOI":"10.1177\/09544062241233924","article-title":"BiLSTM-MLP based hysteresis modeling for soft pneumatic joint actuator","volume":"238","author":"Liu","year":"2024","journal-title":"Proc Inst Mechan Eng Part C"},{"key":"B23","doi-asserted-by":"publisher","first-page":"1189","DOI":"10.1016\/j.ijforecast.2023.10.008","article-title":"Short-term stock price trend prediction with imaging high frequency limit order book data","volume":"40","author":"Ye","year":"2024","journal-title":"Int J Forecast"},{"key":"B24","doi-asserted-by":"publisher","first-page":"400","DOI":"10.1016\/j.procs.2019.01.256","article-title":"Stock market prediction based on generative adversarial network","volume":"147","author":"Zhang","year":"2019","journal-title":"Procedia Comput Sci"},{"key":"B25","first-page":"18","article-title":"Stock price prediction with LSTM based deep learning techniques","volume":"2","author":"Sathish","year":"2021","journal-title":"Int J Adv Sci Innov"},{"key":"B26","first-page":"1","article-title":"Stock market prediction using bi-directional LSTM","volume-title":"2021 International Conference on Communication information and Computing Technology (ICCICT)","author":"Shah","year":"2021"},{"key":"B27","doi-asserted-by":"publisher","first-page":"9158","DOI":"10.3390\/app14209158","article-title":"A stock prediction method based on heterogeneous bidirectional LSTM","volume":"14","author":"Sang","year":"2024","journal-title":"Appl Sci"},{"key":"B28","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1109\/NILES50944.2020.9257950","article-title":"Deep learning-based stock price prediction using LSTM and bi-directional LSTM model","volume-title":"2020 2nd Novel Intelligent and Leading Emerging Sciences Conference (NILES)","author":"Sunny","year":"2020"},{"key":"B29","doi-asserted-by":"publisher","first-page":"117365","DOI":"10.1109\/ACCESS.2020.3004284","article-title":"Forecasting stock prices using a hybrid deep learning model integrating attention mechanism, multi-layer perceptron, and bidirectional long-short term memory neural network","volume":"8","author":"Chen","year":"2020","journal-title":"IEEE Access"},{"key":"B30","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"B31","doi-asserted-by":"publisher","first-page":"2812","DOI":"10.3390\/math12182812","article-title":"Research on stock index prediction based on the spatiotemporal attention BiLSTM model","volume":"12","author":"Mu","year":"2024","journal-title":"Mathematics"},{"key":"B32","doi-asserted-by":"publisher","first-page":"1076","DOI":"10.1007\/s10489-021-02503-2","article-title":"Convolutional neural network based on attention mechanism and Bi-LSTM for bearing remaining life prediction","volume":"52","author":"Luo","year":"2022","journal-title":"Appl Intell"},{"key":"B33","doi-asserted-by":"publisher","first-page":"673","DOI":"10.1007\/s12652-020-02761-x","article-title":"Improving time series forecasting using LSTM and attention models","volume":"13","author":"Abbasimehr","year":"2022","journal-title":"J Ambient Intell Humaniz Comput"},{"key":"B34","doi-asserted-by":"publisher","first-page":"78423","DOI":"10.1109\/ACCESS.2022.3193643","article-title":"Robust LSTM with tuned-PSO and bifold-attention mechanism for analyzing multivariate time-series","volume":"10","author":"Pranolo","year":"2022","journal-title":"IEEE Access"},{"key":"B35","doi-asserted-by":"publisher","first-page":"96","DOI":"10.3390\/joitmc8020096","article-title":"A new stock price forecasting method using active deep learning approach","volume":"8","author":"Alkhatib","year":"2022","journal-title":"J Open Innov"},{"key":"B36","doi-asserted-by":"publisher","first-page":"218","DOI":"10.3390\/agriculture10060218","article-title":"Identification process of selected graphic features apple tree pests by neural models type MLP, RBF and DNN","volume":"10","author":"Boniecki","year":"2020","journal-title":"Agriculture"},{"key":"B37","doi-asserted-by":"crossref","first-page":"493","DOI":"10.1007\/978-981-13-2285-3_58","article-title":"Stock market price prediction using LSTM RNN","volume-title":"Emerging Trends in Expert Applications and Security: Proceedings of ICETEAS 2018","author":"Pawar","year":"2019"},{"key":"B38","doi-asserted-by":"publisher","first-page":"218","DOI":"10.1016\/j.renene.2021.04.025","article-title":"Sequence-based modeling of deep learning with LSTM and GRU networks for structural damage detection of floating offshore wind turbine blades","volume":"174","author":"Choe","year":"2021","journal-title":"Renewable Energy"},{"key":"B39","doi-asserted-by":"publisher","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":"B40","first-page":"513","article-title":"An exploratory comparison of LSTM and BiLSTM in stock price prediction","volume-title":"International Conference on Information, Communication and Computing Technology","author":"Viet","year":"2023"}],"container-title":["Frontiers in Applied Mathematics and Statistics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fams.2025.1588202\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,4]],"date-time":"2025-06-04T05:40:07Z","timestamp":1749015607000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fams.2025.1588202\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,4]]},"references-count":40,"alternative-id":["10.3389\/fams.2025.1588202"],"URL":"https:\/\/doi.org\/10.3389\/fams.2025.1588202","relation":{},"ISSN":["2297-4687"],"issn-type":[{"value":"2297-4687","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,4]]},"article-number":"1588202"}}