Privacy first feature engineering pipeline transforming PII-rich customer data into analytics ready features without exposing personal identifiers.

Responsible synthetic epidemiological surveillance dashboard with interpretable statistical signals (FastAPI + Next.js).

MVP lab: auditable regularity/quality/reliability analytics for noisy public-transit GPS pings. Live Demo + FastAPI/Next.js.

Decision log for product experiments: hypothesis → evidence → decision → learning. Responsible A/B analysis with guardrails and exportable reports.

Applied causal inference lab for business interventions — Diff-in-Diff, matching, uncertainty and decision memos with declared limitations.