# 443 steps jump in one night!

Congratulations to the winners of this competition, and thanks Kaggle and Favorita for hosting it. My special thanks to @Ceshine and @Lingzhi for sharing their codes.
My code was based on Ceshine's code, I added more features and played with it a lot trying to get better public LB. I had stuck at 0.513 public LB after several tries, and did not have enough time to try other solutions. Fortunately, I jumped 443 steps in private LB that made me smile today!
Here I share some points that I believe to be the reason for my improved performance on the test set:
1- My model is an LGBM model with added features. Latest feature count was near 100 focusing more on daily, weekly and monthly features, plus categorical features focusing on items and stores.
2- Large train size: I increased the train data set to 19 weeks starting from 3/15/2017, and the validation set was the last possible week 7/26/2017. This gave a train set almost 3 times larger than public kernels, and most likely helped me to scape the 'curse of dimensionality' with the increased number of data points. I think there was still room to increase the train data size, specially the available data between 7/26 to 8/15 were not used properly. This could be better handled.
3- Forgetting factor (decay): I weighted early weeks of train data with a lower weight compared to the late weeks. This means that models are trained to be more dependent on the latest customer behavior rather than old patterns. 
I didn't make it to spend time on fine tuning the LGBM model, I wish I had!