Boosting the Accuracy of Stock Market Prediction via Multi-Layer Hybrid MTL Structure
This work addresses stock market prediction for financial analysts, but it is incremental as it combines existing methods like Transformer, BiGRU, and KAN.
The paper tackled the problem of stock market prediction by proposing a multi-layer hybrid multi-task learning framework, achieving an MAE of 1.078, MAPE of 0.012, and R^2 of 0.98.
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 R^2 as high as 0.98, when compared with other competitive networks.