Boosting the Accuracy of Stock Market Prediction via Multi-Layer Hybrid MTL Structure

2025/01/01 by Hong, Yuxi
#FOS: Computer and information sciences #FOS: Economics and business #Machine Learning (cs.LG) #Statistical Finance (q-fin.ST)

paper · doi:10.48550/arxiv.2501.09760

Abstract

Accurate stock market prediction provides great opportunities for informed decision-making, yet existing methods struggle with financial data's non-linear, high-dimensional, and volatile characteristics. Advanced predictive models are needed to effectively address these complexities. This paper proposes a novel multi-layer hybrid multi-task learning (MTL) framework aimed at achieving more efficient stock market predictions. It involves a Transformer encoder to extract complex correspondences between various input features, a Bidirectional Gated Recurrent Unit (BiGRU) to capture long-term temporal relationships, and a Kolmogorov-Arnold Network (KAN) to enhance the learning process. Experimental evaluations indicate that the proposed learning structure achieves great performance, with an MAE as low as 1.078, a MAPE as low as 0.012, and an R² as high as 0.98, when compared with other competitive networks.

Related

• Multi-Agent Stock Prediction Systems: Machine Learning Models, Simulations, and Real-Time Trading Strategies
• Stock2Vec: A Hybrid Deep Learning Framework for Stock Market Prediction with Representation Learning and Temporal Convolutional Network
• Transformer Encoder and Multi-features Time2Vec for Financial Prediction
• Autoencoder based Hybrid Multi-Task Predictor Network for Daily Open-High-Low-Close Prices Prediction of Indian Stocks
• SPH-Net: A Co-Attention Hybrid Model for Accurate Stock Price Prediction