• Created a Forecasting model based on Monte-Carlo Simulation and Logistic Regression for a financial institution to increase the recovery of Non-Performing Assets of the company. Reduced 300+ human hours by implementing the logic using Pyspark over Azure Databricks.• Created common data model (CDM) in SQL for different dimensions of a M&A project. Built and maintained the CICD pipelines, version controlling using Azure DevOps.​• Responsible for creating and managing data pipelines on ADF / Synapse analytics / Fabric.• Doing statistical validation using regression techniques for clients related to the agriculture and climate sectors of UK.

• Worked as an ETL expert to drive integration activities and strategies from the source database to a uniform data warehouse using ETL pipelines and AWS resources such as AWS S3, Redshift PostgreSQL, and MS SQL Server.• Built automation scripts in Python that reduced the implementation time for transferring the data from the source to the company's platform drastically.• Built complex and advanced SQL queries on a large chunk of source data to clean and manipulate data as per the company's platform schema and standards.• Worked on various healthcare file formats like HL7, X12, and 837.• Excellent communication skills, and exposure in all important phases of Data Analysis from Data gathering to finally delivering the transformed data for Client use and forecasting.

• HUHC is a Ghaziabad-based NGO that provides free education to underprivileged children living in various slums across INDIA. • My role was to monitor the Literacy Camps of HUHC across Ghaziabad with a team of 200+ volunteers from different colleges.

1. Conducted observations and prepared reports for Quality Improvement research.2. Performed Quality Control Analysis for raw materials and final products and maintained precise laboratory records according to the company’s specifications.