TRLGEMSTSep 20, 2023

Transformers versus LSTMs for electronic trading

arXiv:2309.11400v133 citationsh-index: 5
Originality Synthesis-oriented
AI Analysis

This work addresses the problem of model selection for electronic trading prediction, but it is incremental as it applies existing methods to financial data with minor architectural tweaks.

This study compared Transformer-based and LSTM-based models for financial time series prediction using high-frequency limit order book data, finding that LSTM-based models performed better and more robustly on tasks like price difference and movement prediction, while Transformers had limited advantages in absolute price sequence prediction.

With the rapid development of artificial intelligence, long short term memory (LSTM), one kind of recurrent neural network (RNN), has been widely applied in time series prediction. Like RNN, Transformer is designed to handle the sequential data. As Transformer achieved great success in Natural Language Processing (NLP), researchers got interested in Transformer's performance on time series prediction, and plenty of Transformer-based solutions on long time series forecasting have come out recently. However, when it comes to financial time series prediction, LSTM is still a dominant architecture. Therefore, the question this study wants to answer is: whether the Transformer-based model can be applied in financial time series prediction and beat LSTM. To answer this question, various LSTM-based and Transformer-based models are compared on multiple financial prediction tasks based on high-frequency limit order book data. A new LSTM-based model called DLSTM is built and new architecture for the Transformer-based model is designed to adapt for financial prediction. The experiment result reflects that the Transformer-based model only has the limited advantage in absolute price sequence prediction. The LSTM-based models show better and more robust performance on difference sequence prediction, such as price difference and price movement.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes