Chandra Shekar Adendla

• Developed and maintained scalable PySpark scripts to process, clean, and transform large datasets for machine learning model training and evaluation.
• Collaborated with data scientists and ML enginners to understand requirements and implement data pipelines that support various machine learning models.
• Optimized and automated data workflows to ensure efficient and reliable data processing, reducing runtime and improving performance.

• Created an ETL pipeline from scratch for Campaign Performance data for various platforms DV360, Ad words, Face book, Campaign manager, etc. Ingesting terabyte of data for numerous advertises using Nifi and AWS Data lake and processing using spark. This helped our client immensely to get insights on campaigns running across different platforms
• Optimized SQL queries and database schemas for performance improvements in data retrieval operations.
• Analyzed user requirements, designed and developed ETL processes to load enterprise data into the Data Warehouse.

• • New York Parking: Worked on New York parking system using hive and analyzed the behavior of car parking and how to handle the car parking in the peak hours of the day and at the weekends.

• Identify potential opportunities to enhance company's Fraud Detection system as well as lead machine learning initiatives involving design, development and deployment of machine learning algorithms helping business to grow and scale.

• Read The Data From HDFS and Used Hive For Retrieving Complex Hive quires

• Used Spark for Transformations and MLIB Library for ML.