Placed in fourth in the 2019 Lyft Data Challenge. The challenge involved recommending a Driver Lifetime Value (the value of a driver to Lyft over the entire projected lifetime of a driver), finding main factors that affect a driver's lifetime value, determining the average projected lifetime of a driver, discovering subsets of drivers with differing characteristics in terms of generating revenue, and making actionable recommendations for Lyft. The findings and results were generated through data analysis and statistical modeling in R and then were drafted into a 5-page write-up. Our final ranking was 4th place out of the 150+ teams that competed from around the United States.
Lyft Website: https://lyftdatachallenge.splashthat.com/
Follow up repository: https://github.com/esm2000/lyft_data_challenge