Implementation of the Temporal Logistic Neural BoF method
This repository demonstrates how to use the Temporal Logistic Neural BoF method to classify limit order book data. Please download the preprocessed data from here and place the .h5 file into the data folder. You can then run the experiments by executing the run_exps.py file. Then you can print the results by running the print_results.py script. The proposed model is implemented in bof_models.py, while training utilities are provided in lob_utils.
If you use this code in your work please cite the following paper:
@article{temporal-bof,
title = "Temporal Logistic Neural Bag-of-Features for Financial Time series Forecasting leveraging Limit Order Book Data",
author = "Passalis, Nikolaos and Tefas, Anastasios and Kanniainen, Juho and Gabbouj, Moncef and Iosifidis, Alexandros",
journal = "Pre-print submitted to Pattern Recognition Letters",
}