Sambhav Mahajan

- Engineered end-to-end data pipelines to capture granular shopper journeys, utilising Big Data architectures (Apache Spark, Hadoop) for large-scale analysis. - Optimised backend infrastructure to efficiently manage, store, and serve complex data solutions, ensuring high performance and reliability. - Developed and refined recommendation engines, leveraging user data to drive personalisation and product discovery.

Built a customer churn prediction model using statistical learning techniques, including classification algorithms and sentiment analysis. ◦ Conducted exploratory data analysis (EDA), feature engineering, and statistical validation to identify key churn drivers. ◦ Evaluated models using precision, recall, and classification metrics to ensure business relevance.