Selected projects · 2024 — 2026

Projects

Selected analytics projects, from workforce research and public data to consumer strategy and an AI product.

Selected projects

2024 — 2026

People analytics · Personal project · Nov 2026

Designed and directed a study of 15 years of OPM Federal Employee Viewpoint Survey data (1.65M responses, 29 agencies) asking whether employees who feel well trained are less likely to plan to leave, with AI-assisted analysis in Python (DuckDB, statsmodels) through a reproducible pipeline.
Found the raw ~23-point gap in intent to leave shrinks to about 5 points after controlling for supervisor support, workload and tenure. Agencies whose development scores rose did not see less leaving the following year (p = 0.81); feeling well trained therefore signals retention risk but is not shown to reduce it on its own.

Public research data · USC Marshall · 2024 — present

Built the public site (Jekyll + GitHub Pages) for a hand-collected dataset on how S&P 500 firms structure their top management, standardized into role categories that stay comparable over time.
Wrote the codebook, coverage and methods pages and how-to guide so outside researchers can use data they never helped collect. The dataset supports a paper in Strategic Management Journal.

Visit the site

AI product · USC Marshall AI Case Competition semifinalist · Fall 2026

Reached the semifinal of the 7th Annual AI Global Business Analytics Case Competition with a 7-person team by building Roundtable, a Discord bot (Python, Claude Code, Gemini) that helps MSBA teams decide together.
Scoped the MVP around private, anonymous decision rounds by mapping team-chat failures to root causes, keeping every decision in members’ hands, and verified the build with 577 automated tests.

Industry partnership · Consumer analytics · Fall 2025

Led data collection and analysis for a 5-person consulting team, benchmarking 200 TikTok videos and surveying 350 US consumers; found a competitor drove ~20× the brand’s TikTok Shop GMV over 28 days.
Identified a pricing sweet spot through price-sensitivity analysis and won client adoption of the team’s pricing plan with recommendations on pricing, bundling and review accumulation.