A Comparison of LSTMs and Attention Mechanisms for Forecasting Financial Time Series
This is an incremental improvement for financial forecasting practitioners.
The paper compared LSTM and attention mechanisms for forecasting financial time series, finding that an LSTM with attention can outperform standalone LSTMs, achieving up to 60% performance on five stocks from the Two Sigma dataset.
While LSTMs show increasingly promising results for forecasting Financial Time Series (FTS), this paper seeks to assess if attention mechanisms can further improve performance. The hypothesis is that attention can help prevent long-term dependencies experienced by LSTM models. To test this hypothesis, the main contribution of this paper is the implementation of an LSTM with attention. Both the benchmark LSTM and the LSTM with attention were compared and both achieved reasonable performances of up to 60% on five stocks from Kaggle's Two Sigma dataset. This comparative analysis demonstrates that an LSTM with attention can indeed outperform standalone LSTMs but further investigation is required as issues do arise with such model architectures.