Marrapu Yashwanth

Experience

• 

  Tata Consultancy Services

  May 2019 - Sept 2021

  Data Analyst / IAM Analyst

  • Performed extensive data analysis on user access and roles to identify security risks, leading to a 90% improvement in security and risk mitigation.• Developed advanced SQL queries to gather HR events, identity, and access data, which streamlined HRBP workloads by 10%.• Collaborated with business stakeholders to validate and reconcile data, ensuring accuracy and alignment with business requirements.• Worked with application teams and clients to address identity data quality issues and implemented effective workarounds.• Developed custom dashboards using Python to track key performance indicators (KPIs) and to communicate insights to business stakeholders. Show less

• 

  INeuron.ai

  Oct 2022 - May 2023

  Data Scientist

  Customer Personality Analysis:• Business Problem: Lack of customer insights hinders personalized marketing strategies and exceptional customer experiences, necessitating the implementation of a customer personality analysis project to segment customers based on preferences and behaviors.• Employed a combination of qualitative and quantitative research methods, to collect comprehensive customer data, which in turn passed into various components like data preprocessing and feature engineering to utilize for segmentation and classification.• Utilized K-means clustering algorithm and it’s variations to segment customers into distinct groups based on their preferences, behaviors, and demographics.• Developed the end-to-end Machine Learning Solution using Flask framework and Successfully Deployed the Application in Google Cloud Platform (GCP) services which made it Live for the public.• After utilizing the multiple machine learning models, Adaboost algorithm has outperformed with accuracy of 99.8%. Show less

• 

  ADP

  Jul 2023 - now

  Data Engineer

  • Designed and implemented ETL workflows in PySpark to extract, transform, and load data from multiple sources into data lakes (delta tables) and warehouses.• Built automated data validation frameworks using SparkSQL and PySpark, ensuring data integrity, data accuracy, data quality checks and reliability throughout the ETL pipelines.• Developed complex queries, scripts and automated periodic reports using SQL and Python, saving 4 hours of manual work per week. • Developed and orchestrated data pipelines using Apache Airflow, automating complex ETL workflows and improved overall data pipeline efficiency by 30%.• Developed complex SQL queries for business intelligence reports and dashboards, providing actionable insights to stakeholders in marketing and finance.• Designed and implemented robust data models to improve data organization, accessibility for analytics and reporting and reducing query execution time by 20%.• Developed machine learning model for data quality validation within ETL pipelines, effectively minimizing processing delays caused by data inconsistencies and enhancing overall workflow efficiency. Show less