About
Python, SQL, Power BI and Tableau are the tools. The output is a clear answer to a real business question — and a dashboard or model your team can keep using.
Selected data intelligence projects
Seven of these nine case studies use synthetic data generated for the project. Each GitHub README states its data source and limitations.
- AI Business Intelligence Copilot (synthetic data). Natural-language analytics on governed metrics: root-cause investigation, anomaly detection and forecasting, with every number in an answer checked against the query behind it.
- Predictive Customer Lifetime Value & Revenue Forecasting (synthetic data). LightGBM forecasts next-12-month revenue for every customer, with SHAP drivers, conformal prediction intervals and leakage-safe temporal validation.
- Industrial AI Predictive Maintenance (synthetic data). Calibrated failure-risk forecasts for a 5,000-machine fleet, explained with SHAP and turned into a capacity-constrained weekly maintenance plan. RUL is validated on NASA C-MAPSS.
- SaaS Churn, Retention & Revenue-Risk Analytics (synthetic data). SQL + Python pipeline with machine-learning churn models, probability calibration and causal uplift analysis on subscription, usage and revenue data.
- Retail Demand Forecasting & Inventory Optimization (synthetic data). ML demand forecasting with hidden-demand estimation for stock-outs, replenishment analytics and Power BI-ready reporting.
- Financial Fraud Detection & Transaction Risk (synthetic data). Classifiers plus anomaly detection, explained with XAI, and investigation-queue optimisation on transaction data.
- B2B Sales Pipeline & Revenue Intelligence (synthetic data). Lead scoring with calibrated ML, revenue forecasting, sales-capacity optimisation and next-best-action logic.
- Cybersecurity Threat Detection & SOC Analytics. Security-event analytics that surface correlated, high-severity activity from log data and prioritise analyst response.
- E-commerce Growth & Profitability Analytics. End-to-end case study across customers, products, marketing and returns — cleaning, KPI modelling and exploratory analysis.
Explore more projects on GitHub