This challenge is part of the Driven Data Competition Pump it Up: Data Mining the Water Table which uses data from Taarifa and the Tanzanian Ministry of Water. The task is to search for data driven solutions to predict which waterpoints will fail in order to improve maintenance operations and ensure clean potable water availability for the communities across Tanzania.
The task is a multi-class classification problem to predict the state of water pumps in Tanzania into three categories: working, need repair, and fail. This report provides an explanation of feature analysis, machine learning process and evaluation of results.