Graduate student in Information Management at the University of Illinois Urbana-Champaign specializing in data pipelines, analytics engineering, business intelligence, and applied statistical modeling.
I work primarily with SQL, Python, dbt, BigQuery, and Power BI. My experience focuses on architecting dimensional models (star schemas), building automated ETL/ELT pipelines, cross-system data reconciliation, and implementing statistical experimentation and time-series forecasting models.
End-to-end operational analytics platform integrating WMS order fulfillment, TMS shipments, and simulated ERP item master data. Implements cross-system reconciliation, operational KPI tracking (inventory turns, cycle times, fill rates, on-time delivery), and an executive Power BI star schema model. Technologies: Python, FastAPI, Pandas, Power BI, DAX, Pytest
Analytics engineering pipeline modeled on marketplace transaction dynamics. Extracts creator and show metadata via the iTunes Search API, generates synthetic listener and impression events, models dimensional tables in dbt on Google BigQuery, and automates daily CI/CD pipeline runs. Technologies: dbt, Google BigQuery, Python, GitHub Actions, Looker
Quantitative time-series pipeline examining the relationship between the NY Fed Global Supply Chain Pressure Index (GSCPI) and US Consumer Price Index (CPI) inflation. Features stationarity tests (ADF), Granger causality validation, Vector Autoregression (VAR) 12-month forecasting, and a Streamlit dashboard with automated monthly GitHub Action refreshes. Technologies: Python, Statsmodels, Scikit-learn, Streamlit, Power BI, GitHub Actions
Competitive intelligence benchmark analyzing 598K CFPB consumer complaints and 2M mobile app store ratings across six major US institutions (BofA, Chase, Wells Fargo, PNC, Fifth Third, Truist). Includes a quantitative RICE prioritization framework and automated monthly data refresh deployed to GitHub Pages. Technologies: JavaScript, Node.js, REST APIs, GitHub Pages
Analytics framework for customer journey and A/B experimentation using real Google Analytics 4 (GA4) event data. Features dbt models for funnel and cohort retention alongside a Python statistical library for power analysis, hypothesis testing (two-proportion z-test, Welch's t-test, Mann-Whitney U), Benjamini-Hochberg FDR correction, and Difference-in-Differences estimation. Technologies: Python, dbt, Google BigQuery, SciPy, Statsmodels, Pytest
Securitization data ingestion pipeline and reconciliation engine processing SEC EDGAR ABS-EE loan-level disclosures. Normalizes subprime auto loan datasets into SQLite, validates cross-field discrepancies, and models loan performance metrics for Power BI portfolio analysis. Technologies: Python, SQLite, SEC EDGAR, Power BI
- Languages & Frameworks: SQL, Python, R, JavaScript, HTML, CSS, FastAPI
- Data & Analytics Engineering: dbt, Google BigQuery, PostgreSQL, SQLite, Star Schema Modeling, ETL/ELT
- Statistical Modeling & ML: SciPy, Statsmodels, NumPy, Pandas, Scikit-learn, Time-Series (VAR), A/B Testing
- Business Intelligence & Visualization: Power BI, DAX, Tableau, Streamlit, Plotly
- Infrastructure & Tools: GitHub Actions, Docker, Git, Azure
- LinkedIn: Atharva Sathaye
- Portfolio: atharvasathaye.github.io
- Email: sathaye3@illinois.edu