Projects

Notebook-driven causal inference projects and AI systems case studies.

These projects are written as case studies rather than notebook dumps. The notebook-driven projects show complete causal workflows: a decision question, estimand, assumptions, diagnostics, estimation, sensitivity checks, and a decision-oriented conclusion.

Notebook-Driven Causal Inference Projects

Causal effect of ranking position on clicks

A notebook-driven causal inference project estimating whether top-3 recommendation exposure increases click probability in MIND impression logs.

Apr 26, 2026

Off-policy evaluation for recommendation systems

Causal Inference

Off-Policy Evaluation

Recommender Systems

Doubly Robust

Causal ML

A causal ML project estimating counterfactual recommendation-policy value from logged bandit data with IPS, SNIPS, direct method, doubly robust OPE, and support diagnostics.

Apr 27, 2026

Long-term causal effects of recommendation exposure

Causal Inference

Longitudinal Data

Marginal Structural Models

G-Computation

A sequential causal project estimating whether short-term recommendation exposure affects longer-term engagement and retention-style outcomes.

Apr 28, 2026

Interference and spillover effects in recommendation surfaces

Causal Inference

Interference

Spillovers

Recommendation Systems

A project studying how promoting one item affects both that item and nearby competing items when recommendation units interfere.

Apr 29, 2026

Discovery quality mediation and durable user value

Causal Inference

Mediation

Recommendation Systems

Metrics

A mediation project asking whether broader discovery exposure creates future value directly or indirectly through same-day satisfaction depth.

Apr 30, 2026

AI Systems & LLMOps Case Studies

These pages keep the broader AI portfolio visible: retrieval systems, agentic workflows, multimodal systems, evaluation, monitoring, and deployment thinking.