For this Kaggle competition, you will be using 500ms aggregate "high" frequency order book data of a futures contract to predict future 1-second price changes.
Each row of data represents one snapshot in time. For the label "y", an entry of "1" means the "mid" price will go up (strictly up), and "0" means the mid price will either not move or go down. You should predict the relative probability of a "1" at each timestep of the test set.
There can be 12 submissions per day per team and submission window will close on Thursday 13 FEB 2020 at 2:00PM PST.
You may not use any additional data sources.
Acknowledgements
We thank Jim for providing this dataset.
### Non-enrolled entries will be aggregated into a TA benchmark (grey) and will not count towards student scores.

The average student is not expected to reach this aggregate, since non-enrolled people usually have significantly more experience.