Shruti Ravichandran

Experience

• 

  ZS

  Aug 2020 - Jul 2022

  • Trained junior team members in using SQL and Python for big data analytics and implementing robust quality checks• Analyzed 1B+ payer claims on Redshift to identify a confident Glaucoma patient pool for creating disease journey archetypes • Used NLP algorithm Word2Vec, Convolutional Neural Network (CNN) Autoencoder and Kmeans clustering to segment treatment journeys and created 200+ cluster profiling metrics• Interpreted the results from a self-supervised PU Learning model to identify drivers and barriers to brand adoption• Designed storyboards on PowerPoint and presented project outcomes to client stakeholders from diverse backgrounds Show less • Built a Machine Learning based customer targeting solution to tailor recommendations for physicians who treat leukemia • Wrangled 100M+ patient insurance claims using Spark SQL and Python on Databricks to capture disease journeys• Employed XGBoost and RandomForest to build classification models for predicting likelihood of cancer progression• Applied K-means clustering and networkx community detection to identify influential physicians and their customer persona• Owned the build of end-to-end big data and machine learning pipeline to generate bi-weekly customer targeting insights• Achieved a 50% reduction in run-time by implementing Spark optimization techniques during operationalization• Won ‘Project Champions’ award and ‘valuable contribution to RWD&I space’ award in 2021 Show less

  • Decision Analytics Associate Consultant

    Jun 2022 - Jul 2022

  • Decision Analytics Associate

    Aug 2020 - Jun 2022
• 

  National Center for Supercomputing Applications

  Aug 2022 - Dec 2022

  Project Coordination Intern, Midwest Big Data Innovation Hub

  Coordinated with student groups across Midwestern Universities and facilitated webinars on data-driven research projects as a Project Coordination Intern for Midwest Big Data Innovation Hub, an NSF backed institution, in 2022

• 

  Illinois State Water Survey

  Sept 2022 - Aug 2023

  Data Analyst

  • Assisting with development of Watershed models to simulate the impact of conservation practices on water quality in Illinois• Replicated real-life crop rotation and tillage management practices since 1981 across 9 watersheds by creating python scripts for generating custom inputs based on different watershed parameters• Built ETL pipeline for extracting and combining data spread across 100+ files for user-defined watersheds and parameters

• 

  AGCO Corporation

  May 2023 - Oct 2024

  Data Engineer

  • Enhanced AGCO's Grain and Protein data reporting by working on transforming its data management approach• Harmonized SharePoint data across 15 countries via Python scripts on AWS Lambda, transferring it into AWS S3• Bolstered ETL security by leveraging AWS SSM for encrypted SharePoint credential storage• Deployed AWS Glue crawlers for S3 data extraction, creating Athena tables and populating Redshift staging with Glue ETL• Achieved full automation with a trigger-based AWS Glue Workflow data pipeline integrating the processes above• Authored PL/pgSQL stored procedures to refine data within Redshift staging into tailored business reporting structures• Unified reporting for over 30 KPIs across seven domains such as Operations and Safety using Tableau Dashboards Show less

• 

  CVS Health

  Oct 2024 - now

  Data Engineer