# A silver solution (31st place)

It's time to share about solutions after this great challenge. Here is an insight of my models:
![enter image description here](assets/7fc7b6724134c9bc4aaa8f1a.png)
A few different models followed by simple stacking with a CatBoost. My driver was diversity. 
Each model tuned with stratified CV5 and used to compute OOF for final stacking. Stratification is based on day of week + bin of deal probability.
A few words about important items of each model:
LGB: Based on pymorphy2 text normalization + TF-IDF + categories, images features (NIMA scores, INet scores and basic statistics).
VGG16 features not used. SVD not used. Public LB 0.2200
A set of NN with RNN (BiGRU, BiLSTM), embeddings and dense layers. 
RNN are based on fixed W2V and/or FastText (trained from all title + description available).
The one relying on Capsules provided best results (LB 0.2198). Other with Attention Context scored LB 0.2207.
Last one with Conv2D scored 0.2212. One key point for NN was to take care of categories embedding dimensions.
Stacked XGB with mix of target encoding, TF-IDF and WordBatch (seen in kernels). It scored LB 0.2201.
Finally, main features + each model prediction were used as inputs of a CatBoost model that scored public LB 0.2171 (private 0.2210) and reached 32nd place.
From what I already read in published solutions I should have spent more time on target encoding with different levels as it was key.
I also tried a second layer of stacking (not in the picture) but results were comparable, so I published the simplest one.
I had a lot of fun with this competition, I was my first steps with RNN and NLP, I learned a lot from kernels and discussions here. Thanks to all competitors!