Financial Time Series Forecasting using CNN and Transformer
This work addresses the challenge of accurate stock price forecasting for financial decision-makers, but it is incremental as it combines existing CNN and Transformer techniques.
The paper tackled the problem of forecasting financial time series by modeling both short-term and long-term dependencies, proposing a hybrid CNN-Transformer method that outperformed statistical and deep learning baselines on intraday S&P 500 stock price change prediction.
Time series forecasting is important across various domains for decision-making. In particular, financial time series such as stock prices can be hard to predict as it is difficult to model short-term and long-term temporal dependencies between data points. Convolutional Neural Networks (CNN) are good at capturing local patterns for modeling short-term dependencies. However, CNNs cannot learn long-term dependencies due to the limited receptive field. Transformers on the other hand are capable of learning global context and long-term dependencies. In this paper, we propose to harness the power of CNNs and Transformers to model both short-term and long-term dependencies within a time series, and forecast if the price would go up, down or remain the same (flat) in the future. In our experiments, we demonstrated the success of the proposed method in comparison to commonly adopted statistical and deep learning methods on forecasting intraday stock price change of S&P 500 constituents.