I build end-to-end analytics systems - clean data in, dashboards and decisions out. Most of my work sits at the intersection of BI (Power BI), analytics engineering (SQL + Python), and applied ML when it adds real value.

If you only click two things: start with Supply Chain Analytics (Azure + Power BI) and MovieLens (deployed Streamlit).

• Supply Chain Disruption Analytics - Azure to Power BI pipeline, KPI monitoring, stats + delay risk modeling (Repo)
• MovieLens Recommender - ALS + hybrid ranking, deployed Streamlit app (Repo)
• Letterboxd Sentiment API - weak labels + NLP model, FastAPI service (Repo)
• Sim2Real Engagement - sim vs real churn signals, Streamlit comparison dashboard (Repo)

• DA/BI: Power BI (DAX), Tableau, KPI reporting, dashboard storytelling
• Analytics: SQL, Python (pandas), experimentation, forecasting
• Data Engineering: ETL/ELT, curated layers (Parquet), data modeling, quality checks
• ML (supporting): NLP, recommenders/ranking, model evaluation, deployment (FastAPI)

• I like projects where metrics tie to real decisions (late delivery risk, churn risk, ranking quality).
• I care about reproducibility: clear READMEs, runnable steps, and basic checks.

• Shipping more BI artifacts: dashboard screenshots, KPI definitions, and DAX notes
• Strengthening data engineering habits: curated layers, data checks, and clean project structure
• Improving project READMEs: clearer results, visuals, and 3-step run instructions
• Adding lightweight automation: GitHub Actions for linting/tests and sanity checks

SQL, Power BI, Excel, Python (pandas, scikit-learn), Streamlit, FastAPI, Snowflake, Azure (ADF/Blob), GitHub Actions

• Email: [email protected]
• LinkedIn: Sanjay Dilip

Outside of work, I like exploring media datasets and building analytics around user behavior.