An End-to-End Structure with Novel Position Mechanism and Improved EMD for Stock Forecasting
This work addresses the challenging problem of stock forecasting for investors and researchers by improving accuracy through better data handling and model integration, though it appears incremental as it builds on existing Transformer-based approaches.
The paper tackles stock movement forecasting by proposing a novel attention-based method that incorporates both stock market and individual stock information, along with an EMD-based algorithm to reduce short-term noise, and demonstrates superior performance on two ETFs over ten years, significantly outperforming state-of-the-art baselines.
As a branch of time series forecasting, stock movement forecasting is one of the challenging problems for investors and researchers. Since Transformer was introduced to analyze financial data, many researchers have dedicated themselves to forecasting stock movement using Transformer or attention mechanisms. However, existing research mostly focuses on individual stock information but ignores stock market information and high noise in stock data. In this paper, we propose a novel method using the attention mechanism in which both stock market information and individual stock information are considered. Meanwhile, we propose a novel EMD-based algorithm for reducing short-term noise in stock data. Two randomly selected exchange-traded funds (ETFs) spanning over ten years from US stock markets are used to demonstrate the superior performance of the proposed attention-based method. The experimental analysis demonstrates that the proposed attention-based method significantly outperforms other state-of-the-art baselines. Code is available at https://github.com/DurandalLee/ACEFormer.