%0 Generic %1 ntakaris2017benchmark %A Ntakaris, Adamantios %A Magris, Martin %A Kanniainen, Juho %A Gabbouj, Moncef %A Iosifidis, Alexandros %D 2017 %K %R 10.1002/for.2543 %T Benchmark Dataset for Mid-Price Forecasting of Limit Order Book Data with Machine Learning Methods %U http://arxiv.org/abs/1705.03233 %X Managing the prediction of metrics in high-frequency financial markets is a challenging task. An efficient way is by monitoring the dynamics of a limit order book to identify the information edge. This paper describes the first publicly available benchmark dataset of high-frequency limit order markets for mid-price prediction. We extracted normalized data representations of time series data for five stocks from the NASDAQ Nordic stock market for a time period of ten consecutive days, leading to a dataset of ~4,000,000 time series samples in total. A day-based anchored cross-validation experimental protocol is also provided that can be used as a benchmark for comparing the performance of state-of-the-art methodologies. Performance of baseline approaches are also provided to facilitate experimental comparisons. We expect that such a large-scale dataset can serve as a testbed for devising novel solutions of expert systems for high-frequency limit order book data analysis.

@misc{ntakaris2017benchmark, abstract = {Managing the prediction of metrics in high-frequency financial markets is a challenging task. An efficient way is by monitoring the dynamics of a limit order book to identify the information edge. This paper describes the first publicly available benchmark dataset of high-frequency limit order markets for mid-price prediction. We extracted normalized data representations of time series data for five stocks from the NASDAQ Nordic stock market for a time period of ten consecutive days, leading to a dataset of ~4,000,000 time series samples in total. A day-based anchored cross-validation experimental protocol is also provided that can be used as a benchmark for comparing the performance of state-of-the-art methodologies. Performance of baseline approaches are also provided to facilitate experimental comparisons. We expect that such a large-scale dataset can serve as a testbed for devising novel solutions of expert systems for high-frequency limit order book data analysis.}, added-at = {2023-04-12T21:16:16.000+0200}, author = {Ntakaris, Adamantios and Magris, Martin and Kanniainen, Juho and Gabbouj, Moncef and Iosifidis, Alexandros}, biburl = {https://www.bibsonomy.org/bibtex/21084e237d3eae2bcd13234670a850a2b/qilinw}, doi = {10.1002/for.2543}, interhash = {161c79160a357fb09304269fe1af645e}, intrahash = {1084e237d3eae2bcd13234670a850a2b}, keywords = {}, note = {cite arxiv:1705.03233Comment: Published: Journal of Forecasting}, timestamp = {2023-04-12T21:16:16.000+0200}, title = {Benchmark Dataset for Mid-Price Forecasting of Limit Order Book Data with Machine Learning Methods}, url = {http://arxiv.org/abs/1705.03233}, year = 2017 }