A PyTorch implementation of Bayesian DeepLOB with uncertainty estimation through dropout layers.
This repository provides a Bayesian extension of the DeepLOB model, incorporating dropout-based uncertainty estimation. It is designed to predict mid-prices in limit order books using the FI-2010 dataset.
[1] Ntakaris, A., Magris, M., Kanniainen, J., Gabbouj, M., & Iosifidis, A. (2018). Benchmark dataset for mid-price forecasting of limit order book data with machine learning methods. Journal of Forecasting, 37(8), 852-866. https://doi.org/10.1002/for.2543
Dataset: FI-2010 Dataset
Preprocessed Version: Google Drive Link
[2] Zhang, Z., Zohren, S., & Roberts, S. (2018). DeepLOB: Deep convolutional neural networks for limit order book forecasting. IEEE Transactions on Signal Processing, 67(11), 3001-3012. https://doi.org/10.48550/arXiv.1808.03668 Original Implementation: DeepLOB GitHub Repository
[3] Zhang, Z., Zohren, S., & Roberts, S. (2018). BDLOB: Bayesian deep convolutional neural networks for limit order books. Third Workshop on Bayesian Deep Learning (NeurIPS 2018), Montreal, Canada. https://arxiv.org/abs/1811.10041
- Use Docutils for attribution
- Add project report