BI analyst working with Power BI, SQL, Python and R. I build dashboards, tools and analyses that turn messy operational data into decisions.
Currently building a Python data orchestration pipeline with proper failure handling: scheduled runs, quarantine and recovery for bad records, schema contracts, and quality checks. It'll be public here once it's in a state worth showing.
Open to BI and analytics roles. Best way to reach me is LinkedIn or email.
TidyLens - A browser-based tool for cleaning datasets and running a first pass of exploratory analysis. It automatically flags both obvious and non-obvious issues (placeholder text masking nulls, encoding defects, duplicate keys, casing variants), applies one-click fixes or user-defined column rules (allow-lists, missing-value handling), then profiles the result with linked histograms, scatter plots, and correlations. → Try it
Food Delivery Operations Dashboard - Three-page Power BI dashboard covering executive KPIs, customer retention, and operational bottlenecks. Found that quarter-over-quarter retention sat near 21% with roughly a third of customers ordering only once, and traced a Q4 decline in SLA attainment to prep-time deterioration at a small group of restaurants.
Walmart Sales in Stormy Weather - End-to-end SQL analysis of how rain and snow events shift product demand across 45 stores. Identified weather-sensitive items, separated snow-driven from rain-driven demand, and found anticipatory buying spikes the day before storms, with recommendations for pre-storm inventory positioning.
Uber Demand Forecasting - Hourly pickup demand forecasting for NYC boroughs, benchmarking exponential smoothing, harmonic regression, ARIMA and neural networks against naive baselines.
Life Expectancy Prediction - Predictive modeling across 179 countries using socio-economic and health indicators, comparing linear regression, regression trees, neural networks and XGBoost.
Power BI and DAX · SQL · Python · R · Excel