%0 Generic %1 wallbridge2020transformers %A Wallbridge, James %D 2020 %K LOB finance time_series %T Transformers for Limit Order Books %U http://arxiv.org/abs/2003.00130 %X We introduce a new deep learning architecture for predicting price movements from limit order books. This architecture uses a causal convolutional network for feature extraction in combination with masked self-attention to update features based on relevant contextual information. This architecture is shown to significantly outperform existing architectures such as those using convolutional networks (CNN) and Long-Short Term Memory (LSTM) establishing a new state-of-the-art benchmark for the FI-2010 dataset.

@misc{wallbridge2020transformers, abstract = {We introduce a new deep learning architecture for predicting price movements from limit order books. This architecture uses a causal convolutional network for feature extraction in combination with masked self-attention to update features based on relevant contextual information. This architecture is shown to significantly outperform existing architectures such as those using convolutional networks (CNN) and Long-Short Term Memory (LSTM) establishing a new state-of-the-art benchmark for the FI-2010 dataset.}, added-at = {2023-04-13T17:04:06.000+0200}, author = {Wallbridge, James}, biburl = {https://www.bibsonomy.org/bibtex/2f16cbe945246f472d2f619cb9adc65d1/qilinw}, description = {Transformers for Limit Order Books}, interhash = {83d81003f8f2d32e1434547c0644e777}, intrahash = {f16cbe945246f472d2f619cb9adc65d1}, keywords = {LOB finance time_series}, note = {cite arxiv:2003.00130Comment: 16 pages, 6 figures}, timestamp = {2023-04-13T17:04:06.000+0200}, title = {Transformers for Limit Order Books}, url = {http://arxiv.org/abs/2003.00130}, year = 2020 }