It estimates a driver's Lifetime Value, i.e., the value of a driver to Lyft over the entire projected lifetime of a driver at Lyft. It uses the given data consisting of Driver IDs, Ride IDs and Ride Timestamps. The work involved providing various insights on data such as the main factors affecting a driver's lifetime value, the average projected lifetime of a driver etc. The drivers were grouped into different clusters using K-means clustering. Actionable recommendations for the business were also provided.
For more information of problem statement, please refer "Lyft Data Challenge First Round Prompt.pdf". For a detailed report of data analysis and results, please refer "cizos_Writeup_AK_AP.pdf".