Football Analytics

I performed football analytics with Premier League Data for the latest 12 seasons data i.e., 2011-2012 to 2022-2023 which contains data on 4451 matches with 21 variables of interest such as corners, fouls, shots on targets, etc. to predict the full time result.

Credit Risk Modeling

We worked with lending history (loans current or defaulted) dataset which has approximately 1.3 million loans and around 128 variables. Using the available data we estimated the capital requirements for Lending Club.

Faulty Pump Prediction

I worked on a predictive modelling (multi-class) problem where I used data from Taarifa and the Tanzanian Ministry of Water, to predict which pumps were functional, which need some repairs, and which don't work at all.