Benchmark Dataset for Mid-Price Prediction of Limit Order Book data

05/09/2017

∙

by   Adamantios Ntakaris, et al.

∙

0

∙

share

Presently, managing prediction of metrics in high frequency financial markets is a challenging task. An efficient way to do it is by monitoring the dynamics of a limit order book and try to identify the information edge. This paper describes a new benchmark dataset of high-frequency limit order markets for mid-price prediction. We make publicly available normalized representations of high frequency data for five stocks extracted from the NASDAQ Nordic stock market. Furthermore, we define an experimental protocol that can be used in order to evaluate the performance of related research methods. Baseline results based on linear and nonlinear regression models are also provided and show the potential that these methods have for mid-price prediction.