融合Transformer、BiGRU与KAN的多层协同模型，显著提升股市预测精度。
Boosting the Accuracy of Stock Market Prediction via Multi-Layer Hybrid MTL Structure
- 分层融合Transformer、BiGRU与KAN，协同捕捉特征与时序关系
- 在真实数据上实现MAE=1.078、MAPE=0.012、R²=0.98的高精度表现
- 适合追求高精度金融预测的量化研究者与投资决策系统开发者
精准的股市预测为理性决策提供重要支持，但现有方法难以应对金融数据非线性、高维和波动性强的特点。本文提出一种新型多层混合多任务学习（MTL）框架，以实现更高效的股市预测。该框架采用Transformer编码器提取多维输入特征间的复杂关联，双向门控循环单元（BiGRU）捕捉长期时间依赖关系，并引入柯尔莫戈洛夫-阿诺德网络（KAN）优化学习过程。实验表明，所提结构在多个基准模型中表现优异，测试集上达到最低1.078的平均绝对误差（MAE）、最低0.012的平均绝对百分比误差（MAPE），以及最高0.98的决定系数（R²）。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。