# The 92nd place and 378 positions up on private leaderboard

I don't have too much experience with time series classification tasks so I decided to go with a pretty simple approach. I used
tsfresh
library to extract a set of features from time series data. Also, the library helps to pick only relevant features among extracted using null-hypothesis testing framework. Then I trained a LightGBM classifier using the extracted features.​
[This kernel shows](https://www.kaggle.com/purplejester/the-best-friend-of-an-alchemist?scriptVersionId=12730118)
an example of this approach. The kernel gives
0.59
on private. However, if you extract more features, pick only the relevant ones, tune the classifier parameters and use k-fold validation, you'll probably get something around
0.66
. (I am attaching a submission file that gives me that score on private).
Though this solution is far away from the top positions, it is very straightforward and could be implemented within a couple of hours. So it seems to be a good baseline solution for time series classification problems.