# 41th place (without using data leakage!)

The results on the private part of the test are really unexpected for me.
For the final submission I have used 2 solutions
1) one with data leakage (using the ideas from this kernel by Markus F
[https://www.kaggle.com/friedchips/the-missing-link](https://www.kaggle.com/friedchips/the-missing-link)
For this submission I got 0.82 on the dataset and was sure that it would be my best solution, but on the private set it got only 0.60. It is really a puzzle for me to understand this result, I still have no idea about it.
2) one without using data leakage. I selected my kernel with neural network, mostly wondering how efficient NN can be on such a small dataset. And it worked rather good! I got 0.71 on the public set, the same score I got on the public set
[https://www.kaggle.com/skondrash/nn-lstm-fft-features?scriptVersionId=12728595](https://www.kaggle.com/skondrash/nn-lstm-fft-features?scriptVersionId=12728595)