I analyze, model, and visualize data to uncover insights that improve operations and growth. Explore selected projects spanning SQL analytics, Excel automation, Tableau stories, and Power BI dashboards.
Built SQL queries to engineer churn features, segmented customers, and visualized drivers to reduce churn risk. Identified 3 key predictors improving retention targeting by 18%.
Cleaned and modeled Superstore data; built an Excel forecasting dashboard with seasonality controls and KPI alerts, reducing manual reporting time by 30%.
Built SQl queries to analyze customer spendings, revenuew by country and genre plus Sales trends.
Problem: Identify drivers of churn and prioritize retention actions.
Data & Tools: SQL (feature engineering), Tableau (visual story), Excel (QA checks).
Approach: Cleaned joins; computed tenure, usage deltas, and support-touch frequency; segmented users with cohort analysis; built KPI views.
Results: Surfaced 3 drivers (support touches, contract type, tenure<12m). Proposed playbook reduced at‑risk cohort by 18% in pilot.
What I’d do next: Add survival analysis and uplift modeling to optimize offers.
Churn analytics, retail forecasting, KPI dashboards, and ETL automation.
Download my latest resume: