- Worked on integrating data from various sources into a unified MDM system by implementing pipelines that extract, transform, and load data (ETL), ensuring that the data is accurate and the process is efficient.- Developed various statistical analysis to evaluate government welfare program usage and participant engagement, provided critical insights that informed recommendations for program management and development.- Developed various models to examine the transaction history of customers already benefitting from government social programs, enhancing the accuracy of eligibility assessments.- Designed and created data ingestion pipelines using Informatica, PySpark, SQL and python resulted in clean and easily monitored processes and transformed them into insightful, interactive visualizations by using Tableau.- Developed rules and algorithm for data quality monitoring system and deployed the model as a microservice API that is used by other divisions, ensuring consistent data integrity and quality.Tools Used:Programming: Python, SQL, PysparkSoftware: Informatica, AtScale, IBM Datastage.Visualization: TableauDatabases: PostgreSQL, MySQL.Analytical Techniques: Machine Learning, Regression Analysis, Classification, Clustering.Big Data Technologies/Environments: Hadoop, Spark, Hive, Impala.

Analyze and increase the plant production efficiency by minimizing waste, successfully digitize the maintenance reporting system, create and lead the implementation of TPM