# escalated chi: 2nd place solution

I was reading raddar's post about their advance data exploration and inference about the anonymous feature sets, I must admit you guys did a fantastic job there. In contrast, we did not invest much time on EDA as we found out likelihood encoding of interactions improving the result exponentially in the early stage of the competition. Since then, I mostly focused on creating different representation of the interactions in different levels and Daniel took care of the Stacking and ensembling part. Jeremy (idle_speculation) also had a fantastic set of features which helped us in the later stage of the competition. the image below illustrates our workflow in a nutshell:
![enter image description here](https://i.imgsafe.org/91d5795.png)
We also tried a lot of other things but didn't have much time to finish training on them- especially worth mentioning RGF. As already noted in the forum, performance wise it was almost on par with XGB but very slow.
I extend my greetings to the other winners and thank Kaggle and BNP Paribas for hosting such a nice competition. I would also like to thank my teammates Daniel and Jeremy for their valuable contributions.
Last but not the least, Laurea - keep rocking :)