DeepLOB: Deep Convolutional Neural Networks for Limit Order Books

Zihao Zhang, Stefan Zohren, Stephen Roberts · 2019 · IEEE Transactions on Signal Processing

AdvancedHFTEmpiricalFree to read

CNN plus inception module plus LSTM on the top 10 book levels to predict mid-price direction. The most-cited deep LOB model and the usual baseline.

Read the paper ↗Free version ↗

At a glance

Level: Advanced: Stochastic control, point processes, heavy econometrics or deep learning
Horizon: HFT
Data needed: L2 depth (snapshots) Set what data you have
Themes: Machine learning Order-flow alpha
Assets: Equities
Market: Europe

Your notes

Report a problem with this entry

Step 3 of 6 in

Deep learning on the order book (with a reality check)

← Benchmark dataset for mid-price forecasting of limit order book data with machine learning methodsUniversal features of price formation in financial markets: perspectives from deep learning →

Cite

@article{zhang2019deeplob,
  author = {Zhang, Zihao and Zohren, Stefan and Roberts, Stephen},
  title = {{DeepLOB: Deep Convolutional Neural Networks for Limit Order Books}},
  journal = {IEEE Transactions on Signal Processing},
  year = {2019},
  doi = {10.1109/tsp.2019.2907260}
}

Zhang, Z., Zohren, S., & Roberts, S. (2019). DeepLOB: Deep Convolutional Neural Networks for Limit Order Books. IEEE Transactions on Signal Processing. https://doi.org/10.1109/tsp.2019.2907260