Avinandan Dutta

Data Scientist (2 yrs) who operationalizes ML/NLP for clinical trials—RAG/LLM pipelines, cohort generation, protocol/ICD/SNOMED mapping, and patient/diversity analytics. Stack: Python, SQL, PySpark, Snowflake/Databricks, Power BI/Tableau. Proven 3× speedups and $10M+ impact.

Data Scientist with ~2 years’ experience converting clinical-trial, EHR, and claims data into production analytics. I operationalize LLM/RAG pipelines, cohort generation, and ICD-10/SNOMED/MeSH mapping; standardize 200+ protocol attributes from Citeline/ClinicalTrials.gov; and deliver patient-burden & diversity analytics used across 20+ engagements.

Track record: 3× faster pipelines, 40% quicker delivery, 90% null reduction, and $10M+ impact.

Stack: Python, SQL, PySpark, Snowflake/Databricks, scikit-learn, Power BI/Tableau.

• M.A. in Applied Economics, Christ (Deemed to be) University, Bangalore — rigorous training in statistics, econometrics (cross-section/panel), regression modeling, time-series (ARIMA/VAR), and ML fundamentals; hands-on work in Python/R/SQL and empirical projects linking healthcare and policy analytics.
• B.Sc. (Hons) in Economics, Scottish Church College — strong quantitative foundation; coursework in probability, inference, optimization, econometrics, and data analysis.
• Analytics internship (graduate) — applied Python/SQL for data wrangling and regression/time-series studies; delivered Tableau/Power BI dashboards and an NLP sentiment mini-project.
• Relevant certifications: Google Data Analytics (Professional), Generative AI Fundamentals (Google), SQL for Data Science.