# The way to the 18th place, just for rookies.

First of all, congratulations to all of you guys who put great effort and learned a lot of new things from this competition. I had a great fun and meet new friends here, so lucky.
Now comes the solution of our team, which should be simple without any magic. The steps are:
Best single model part (LGB):
Folked the public kernel and did some research such as parameter tuning which gave us a slightly better result than all the public kernels.
Doing more feature engineering such as keywords count, text hash,  categorical feature hash.
We found the price and item_seq_number features were interesting. We applied exponential and linear segmentation of them and adding the segmented data as new categorical features.
We added "char" level analyzer for TFID process.
Target encoding.
Applying external data. we found the "income", "population" features are helpful. The Location Information did not help us.
Adding basic image features based on public kernels.
Final parameter tunning.
This model helped us to score 0.2184 after doing a 5-folds average. But it needs 3 hours to run on a 20 core server for each fold.
NN part:
We used most the similar features for NN, which gave us a 0.2205 score on LB. By a simple stacking of the LGB and NN models, we got 0.2179 and after some blending, we got 0.2176 on LB.
Team up part:
It was so lucky for us that @Yuki.O joined us. He is a genius guy who did massive feature engineering which makes the big diversity between our models. A simple stack gave us 0.2169 on the public LB.
Stacking part:
In the last week, we start to stack all the models. We created aprrox. 40 models with catboost, FM, mlp, LSTM. I think because it was limited by our best single model, the can just reach 0.2156 on the public LB. We fight till the last minutes though. :P
Ok, this is all about what we did in this competition, great fun! Many thanks to all of you guys
[@huiqin](/huiqin)
, @Steeve Huang,
[@steinhafen](/steinhafen)
, and
[@extremin](/extremin)
. Special thanks to my new friend @Yuki.O, who put lots of effort into this competition and I learned a lot from him, not only the knowledge but also the professional attitude.