# 110th Place Solution

I briefly write down my solution, which got medal-border score.
So, this is not a complex approach.
Feature Engineering
: based on
[this kernel](https://www.kaggle.com/yoshoku/gacrp-v2-starter-kit)
Modeling...Classification => Regression
: As discussed
[here](https://www.kaggle.com/c/ga-customer-revenue-prediction/discussion/71427)
, after classifying whether the re-visited purchase will occur or not, I made a regression model which predicts how much the amount of the purchase is.
Task Timeframe
: In this task, we have to predict the amount of the purchase from 2018/12/01 to 2019/1/31 per user who has visited between 2018/5/1 and 2018/10/15 with the data whose timeframe is from 2016/4/1 to 2018/4/30 and from 2018/5/1 to 2018/10/15.
Validation Strategy
: To consider the problem simply, aiming to ignore the seasonality, I decided to take the following validation strategy:
The task is to predict whether re-visited purchase will occur or not between 2018/12/1 and 2019/1/31 by using data whose timeframe is from 2018/5/1 to 2018/10/15.
For validation, I predicted the probability of the occurrance of re-visit between 2017/12/1 and 2018/1/31 by using data whose timeframe is from 2017/5/1 to 2017/10/15 (just a year ago).
In this competition, the principal, "Trust Your CV", was also true, as the Public LB was no use. So, the validation strategy was so critical that I want to know how other people took the approach. (However the luck might be most important. Is it true or not? )
Thanks for reading and welcome any comments!