Designed and maintained 10+ ETL pipelines using PySpark and GCP services (BigQuery,Dataflow, Dataproc, Cloud Storage) to improve data integration and performance.

Spearheaded the migration of ETL processes to GCP, achieving a 95% reduction in manualintervention.

Designed PySpark & SQL-based data pipelines for insurance call center analytics.

Enhanced call quality analysis by transitioning stored procedures to Python.

Optimized reporting and data visualization using Power BI & SQL.

Predicts the rate of different categories of areca nut in different cities. The output is given for 10 different cities and 6 different categories of areca nuts

Presale scoring for the car showrooms if man purchases a car or not. It's based on various parameters like previous car, color, financial status of the party etc.

Worked on different bank transactions and categorized those transactions through awk scripting. This helped the Insight team to understand different categories of bank transactions, which resulted in improving the bank statement related code.