DeepLOB: Deep convolutional neural networks for limit order books
We develop a large-scale deep learning model to predict price movements from limit order book (LOB) data of cash equities. The architecture utilizes convolutional filters to capture the spatial structure of the LOBs as well as long short-term memory modules to capture longer time dependencies. The p...
Main Authors: | , , |
---|---|
Format: | Journal article |
Published: |
IEEE
2019
|
_version_ | 1797065471939313664 |
---|---|
author | Zhang, Z Zohren, S Roberts, S |
author_facet | Zhang, Z Zohren, S Roberts, S |
author_sort | Zhang, Z |
collection | OXFORD |
description | We develop a large-scale deep learning model to predict price movements from limit order book (LOB) data of cash equities. The architecture utilizes convolutional filters to capture the spatial structure of the LOBs as well as long short-term memory modules to capture longer time dependencies. The proposed network outperforms all existing state-of-the-art algorithms on the benchmark LOB dataset [A. Ntakaris, M. Magris, J. Kanniainen, M. Gabbouj, and A. Iosifidis, “Benchmark dataset for mid-price prediction of limit order book data with machine learning methods,” J. Forecasting, vol. 37, no. 8, 852-866, 2018]. In a more realistic setting, we test our model by using one-year market quotes from the London Stock Exchange, and the model delivers a remarkably stable out-of-sample prediction accuracy for a variety of instruments. Importantly, our model translates well to instruments that were not part of the training set, indicating the model's ability to extract universal features. In order to better understand these features and to go beyond a “black box” model, we perform a sensitivity analysis to understand the rationale behind the model predictions and reveal the components of LOBs that are most relevant. The ability to extract robust features that translate well to other instruments is an important property of our model, which has many other applications. |
first_indexed | 2024-03-06T21:29:08Z |
format | Journal article |
id | oxford-uuid:4411af59-2657-4e3e-8ee2-81032c37671c |
institution | University of Oxford |
last_indexed | 2024-03-06T21:29:08Z |
publishDate | 2019 |
publisher | IEEE |
record_format | dspace |
spelling | oxford-uuid:4411af59-2657-4e3e-8ee2-81032c37671c2022-03-26T14:59:28ZDeepLOB: Deep convolutional neural networks for limit order booksJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:4411af59-2657-4e3e-8ee2-81032c37671cSymplectic ElementsIEEE2019Zhang, ZZohren, SRoberts, SWe develop a large-scale deep learning model to predict price movements from limit order book (LOB) data of cash equities. The architecture utilizes convolutional filters to capture the spatial structure of the LOBs as well as long short-term memory modules to capture longer time dependencies. The proposed network outperforms all existing state-of-the-art algorithms on the benchmark LOB dataset [A. Ntakaris, M. Magris, J. Kanniainen, M. Gabbouj, and A. Iosifidis, “Benchmark dataset for mid-price prediction of limit order book data with machine learning methods,” J. Forecasting, vol. 37, no. 8, 852-866, 2018]. In a more realistic setting, we test our model by using one-year market quotes from the London Stock Exchange, and the model delivers a remarkably stable out-of-sample prediction accuracy for a variety of instruments. Importantly, our model translates well to instruments that were not part of the training set, indicating the model's ability to extract universal features. In order to better understand these features and to go beyond a “black box” model, we perform a sensitivity analysis to understand the rationale behind the model predictions and reveal the components of LOBs that are most relevant. The ability to extract robust features that translate well to other instruments is an important property of our model, which has many other applications. |
spellingShingle | Zhang, Z Zohren, S Roberts, S DeepLOB: Deep convolutional neural networks for limit order books |
title | DeepLOB: Deep convolutional neural networks for limit order books |
title_full | DeepLOB: Deep convolutional neural networks for limit order books |
title_fullStr | DeepLOB: Deep convolutional neural networks for limit order books |
title_full_unstemmed | DeepLOB: Deep convolutional neural networks for limit order books |
title_short | DeepLOB: Deep convolutional neural networks for limit order books |
title_sort | deeplob deep convolutional neural networks for limit order books |
work_keys_str_mv | AT zhangz deeplobdeepconvolutionalneuralnetworksforlimitorderbooks AT zohrens deeplobdeepconvolutionalneuralnetworksforlimitorderbooks AT robertss deeplobdeepconvolutionalneuralnetworksforlimitorderbooks |