Improving stock price forecasting with M-A-BiLSTM: a novel approach

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, Mu...

Full description

Saved in:
Bibliographic Details
Main Author: Zihan Liu
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-06-01
Series:Frontiers in Applied Mathematics and Statistics
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fams.2025.1588202/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849736107272437760
author Zihan Liu
author_facet Zihan Liu
author_sort Zihan Liu
collection DOAJ
description 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 (R2) for Apple. Meanwhile, the MSE on the ExxonMobil dataset decreased to 1.8954, showing a significant reduction, while the R2 increased to 0.9887. These results demonstrate the model's superior predictive power, offering a robust and interpretable approach for financial forecasting.
format Article
id doaj-art-b918f10fb9be42e0a02659f290a9c934
institution DOAJ
issn 2297-4687
language English
publishDate 2025-06-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Applied Mathematics and Statistics
spelling doaj-art-b918f10fb9be42e0a02659f290a9c9342025-08-20T03:07:21ZengFrontiers Media S.A.Frontiers in Applied Mathematics and Statistics2297-46872025-06-011110.3389/fams.2025.15882021588202Improving stock price forecasting with M-A-BiLSTM: a novel approachZihan LiuStock 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 (R2) for Apple. Meanwhile, the MSE on the ExxonMobil dataset decreased to 1.8954, showing a significant reduction, while the R2 increased to 0.9887. These results demonstrate the model's superior predictive power, offering a robust and interpretable approach for financial forecasting.https://www.frontiersin.org/articles/10.3389/fams.2025.1588202/fullstock price predictiondeep learningBi-LSTMMLPattention
spellingShingle Zihan Liu
Improving stock price forecasting with M-A-BiLSTM: a novel approach
Frontiers in Applied Mathematics and Statistics
stock price prediction
deep learning
Bi-LSTM
MLP
attention
title Improving stock price forecasting with M-A-BiLSTM: a novel approach
title_full Improving stock price forecasting with M-A-BiLSTM: a novel approach
title_fullStr Improving stock price forecasting with M-A-BiLSTM: a novel approach
title_full_unstemmed Improving stock price forecasting with M-A-BiLSTM: a novel approach
title_short Improving stock price forecasting with M-A-BiLSTM: a novel approach
title_sort improving stock price forecasting with m a bilstm a novel approach
topic stock price prediction
deep learning
Bi-LSTM
MLP
attention
url https://www.frontiersin.org/articles/10.3389/fams.2025.1588202/full
work_keys_str_mv AT zihanliu improvingstockpriceforecastingwithmabilstmanovelapproach