yujia21/INF554-AXA-Data-Challenge

The AXA data challenge aims at developing models for an inbound call forecasting system. The forecasting system should be able to predict the number of incoming calls for the AXA Assistance call center in France, on a per "half-hour" time slot basis. The prediction is for seven (7) days ahead in time. The specific dataset includes telephony data retrieved from AXA call centers, and corresponds to the the period spanning the calendar years 2011-13.

INF554Projet

Due to space constraints, train_2011_2012_2013.csv and data/... files are not included.

Bootstrap.py :

This is the base file for writing the predict functions. (Line 40)

There are three options to play with on line 9 :

imported_data=True True if data/... already exists If False, will run ImportData.py, which takes train_2011_2012_2013.csv and creates data/...

evaluation=True True if want to evaluate error of machine learning algo. Can change the dates called TODO: add Frapy's evaluation function

submit=True True if we want to create a submission file with new prediction values. Dates predicted are always the dates provided in the original submission.txt file