Benchmark dataset for mid-price forecasting of limit order book data with machine learning methods

Adamantios Ntakaris, Martin Magris, Juho Kanniainen, Moncef Gabbouj, Alexandros Iosifidis · 2018 · Journal of Forecasting

IntermediateHFTDatasetFree to read

FI-2010: a public 10-level LOB dataset for five Nasdaq Nordic stocks. The standard (if small) benchmark for LOB models.

Read the paper ↗Free version ↗

At a glance

Level: Intermediate: Comfortable with statistics, regressions and basic probability models
Horizon: HFT
Data needed: L2 depth (snapshots) Set what data you have
Themes: Machine learning
Assets: Equities
Market: Europe

Your notes

Report a problem with this entry

Step 2 of 6 in

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

← Modelling high-frequency limit order book dynamics with support vector machinesDeepLOB: Deep Convolutional Neural Networks for Limit Order Books →

Cite

@article{ntakaris2018benchmark,
  author = {Ntakaris, Adamantios and Magris, Martin and Kanniainen, Juho and Gabbouj, Moncef and Iosifidis, Alexandros},
  title = {{Benchmark dataset for mid-price forecasting of limit order book data with machine learning methods}},
  journal = {Journal of Forecasting},
  year = {2018},
  doi = {10.1002/for.2543}
}

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. https://doi.org/10.1002/for.2543