Dataset for Mid-Price Forecasting of Limit Order Book Data

This is a benchmark dataset for mid-price forecasting of limit order book data. It is a dataset of high-frequency limit order markets for mid-price prediction. The authors 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.