DeepLOB: Deep convolutional neural networks for limit order books
- Submitting institution
-
University of Oxford
- Unit of assessment
- 12 - Engineering
- Output identifier
- 9616
- Type
- D - Journal article
- DOI
-
10.1109/TSP.2019.2907260
- Title of journal
- IEEE Transactions on Signal Processing
- Article number
- -
- First page
- 3001
- Volume
- 67
- Issue
- 11
- ISSN
- 1053-587X
- Open access status
- Compliant
- Month of publication
- March
- Year of publication
- 2019
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- Yes
- Number of additional authors
-
2
- Research group(s)
-
-
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper shows that universal patterns exist in high-frequency limit order books, the canonical auction space for financial trading. It is the first to show transfer learning between asset classes. It forms part of a body of work that helped secure a large (GBP7,000,000+) follow-on funding package from a global hedge fund (Chief Scientist and Academic Liaison, Man Group available to corroborate)
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -