arXiv 20 Sep 2023 · Finance — Trading · 31 citations (OpenAlex)
arXiv:2309.11400 · PDF · DOI · OpenAlex · Extracted main text
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.
appendix boundary found by appendix_command · 99% of the source is main text. Read the extracted text to check this.
The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.
| Reference | Intensity | Mentions | Sections | Main text | |
|---|---|---|---|---|---|
| 1 | Zihao Zhang, Stefan Zohren, and Stephen Roberts (2019) DeepLOB: Deep convolutional neural networks for limit order books | 1.000 | 15 | 5 | 100% |
| 2 | Haixu Wu, Jiehui Xu, Jianmin Wang, and Mingsheng Long (2021) Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting, 2021 | 1.000 | 15 | 4 | 100% |
| 3 | Tian Zhou, Ziqing Ma, Qingsong Wen, Xue Wang, Liang Sun, and Rong Jin (2022) Fedformer: Frequency enhanced decomposed transformer for long-term series forecasting, 2022a | 1.000 | 13 | 4 | 100% |
| 4 | Haoyi Zhou, Shanghang Zhang, Jieqi Peng, Shuai Zhang, Jianxin Li, Hu… (2012) Informer: Beyond efficient transformer for long sequence time-series forecasting, 2020 | 1.000 | 13 | 4 | 100% |
| 5 | Zihao Zhang and Stefan Zohren (2021) Multi-horizon forecasting for limit order books: Novel deep learning approaches and hardware acceleration using intelligent proc… | 1.000 | 12 | 4 | 100% |
| 6 | Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jo… Attention is all you need | 1.000 | 10 | 3 | 100% |
| 7 | Nikita Kitaev, Łukasz Kaiser, and Anselm Levskaya (2001) Reformer: The efficient transformer, 2020 | 1.000 | 7 | 3 | 100% |
| 8 | Shiyang Li, Xiaoyong Jin, Yao Xuan, Xiyou Zhou, Wenhu Chen, Yu-Xiang… (1907) Enhancing the locality and breaking the memory bottleneck of transformer on time series forecasting, 2019 | 1.000 | 6 | 4 | 100% |
| 9 | Petter N. Kolm, Jeremy D. Turiel, and Nicholas Westray (2021) Deep order flow imbalance: Extracting alpha at multiple horizons from the limit order book | 1.000 | 5 | 4 | 100% |
| 10 | Shizhan Liu, Hang Yu, Cong Liao, Jianguo Li, Weiyao Lin, Alex X. Liu… (2022) Pyraformer: Low-complexity pyramidal attention for long-range time series modeling and forecasting | 0.928 | 4 | 3 | 100% |
Showing the top 10 of 63 scored citations.