# 7th place solution

First of all, thank you G-Research and Kaggle for hosting the competition. I really like the data provided in this competition, actual market data give us more room for creative method development and is much more interesting compared with anonymized tabular data.
My approach is 99% on modeling and the only feature I added is the time of day. Here is a very brief description of my model, the final submission is an ensemble of 4 models trained with different sequence lengths.
![](https://i.imgur.com/ECta6Oe.png)