B.Tech IT student focused on SQL, data pipelines, and applied analytics — backed by hands-on work across Python, Power BI, MySQL, and Tableau.
| Project | Business Problem | Tools | Key Result | Link |
|---|---|---|---|---|
| Sales Data Warehouse & Churn Analytics | Built a bronze/silver/gold MySQL warehouse and a churn model to flag at-risk customers before they leave | MySQL · Python · scikit-learn · Power BI | 0.974 ROC-AUC churn model, 4-page executive Power BI report | Repo → |
| Digital Ad Campaign A/B Test | Measured whether Campaign B (Test) actually outperformed Campaign A (Control) across the impressions-to-purchase funnel | Power BI | 4-page Control vs. Test decision dashboard | Repo → |
| Marketing Funnel & Cohort Analysis | Diagnosed where leads drop off in a B2B lead-to-deal funnel (Olist dataset) and tracked conversion by channel and cohort | Excel · Tableau Public | ~10.5% overall conversion; isolated a structural shift starting Jan-2018 | Repo → |
| Student Placement EDA | Identified the strongest predictors of placement outcome and salary from campus placement data | Python (pandas, seaborn) | CGPA & technical skills are the top predictors (r=0.28); placed students averaged 8.43 CGPA vs. 7.52 and 64% fewer backlogs | Repo → |
| Data Professionals Survey Dashboard | Surfaced trends and pay/role patterns from a survey of data professionals | Excel · Power BI | Interactive dashboard mapping salary bands, tool preferences, and job-satisfaction patterns across data roles, with role/gender slicers | Repo → |
Smaller repos that show core data-handling and scripting skills:
| Project | What it does | Link |
|---|---|---|
| IMDb Web Scraping | Scrapes and structures IMDb data with Python + BeautifulSoup | Repo → |
| API to CSV | Pulls movie data from a public API, cleans it with Pandas, exports analysis-ready CSVs | Repo → |
Languages & Query: SQL · Python BI & Visualization: Power BI · Tableau · Excel (PivotTables, XLOOKUP, SUMIFS/COUNTIFS) Data Engineering: MySQL · ETL pipelines · Medallion architecture (bronze/silver/gold) ML: scikit-learn — classification, churn/risk scoring