# Late Submission Socre 0.884 ... And Solution

Thankyou for providing the entrance of late submission. I should trust my model and local cv instead of my intuition. 
In my model, I split the data into 6 groups, 5 group train sets, and 1 validation set.
In each training set, 6 month's aggregrate feature of each id and the next 3 months' sum revenue as target.
The validation set is created by the same method, using 2018.02.01-2018.07.31 data to aggregrate features, using 2018.8.1 - 2018.10.15 's sum revenue as target.
It's difficult for me to explain my solution without code beacuse of my limited English ability ... 
The most importance features are (aggregrated) totals.hits/totals.timeOnSite/totals.pageViews and
heats
which is a feature I made by myself using a linear combination of the number of hit and revenues of each month in the training set (made by pivot table). What about yours?