Markets
International trade, macro context, alternative data, and country or industry screening.
Loading, please wait.
Portfolio · Sangmin Lee
International Trade major and Business Administration double-major candidate, preparing for work across analytics, financial research, and service planning.
The projects cover churn analysis, night-light GDP research, Korean Air financial analysis, a paper-trading system, a photography-commerce MVP, and survey research. When a number could sound like an outcome, I show the caveat beside it.
Working method
How I work
I start by asking why the question matters, then separate what I checked from what still needs another pass.
International trade, macro context, alternative data, and country or industry screening.
Financial statements, valuation logic, sensitivity checks, and assumption audits.
Python, statistics, regression, classification, explainable AI, and survey analysis.
Dashboards, reports, MVP flows, operating checks, and clear next-step recommendations.
Selected evidence highlights
When a number could sound like an outcome claim, I spell out where it came from and what it does not prove. The full cases below carry the detail.
Evidence
What I worked on · Turning satellite climate grids into a decision-grade operating window, with OLS and Theil-Sen required to agree.
Caveat · Physical accessibility under concentration thresholds only; it excludes insurance, escort, and regulatory constraints.
Evidence
What I worked on · Constructing a variable the source data does not contain, finding the first metric broken, and repairing it before reporting.
Caveat · In-progress work ahead of a September 2026 submission; dwell is estimated from gate records, not measured mobility data.
Evidence
What I worked on · Customer segmentation, explainable classification, and action-oriented retention planning.
Caveat · The 5.0 percentage-point churn reduction is a proposed target, not an achieved result.
Evidence
What I worked on · Testing night lights as an auxiliary economic indicator, while separating data QA from model claims.
Caveat · This is explanatory fit in a simple model, not prediction accuracy or causal proof.
Evidence
What I worked on · Financial statement analysis and comparison of DCF, APV, and relative valuation.
Caveat · A conditional classroom analysis; valuation arithmetic requires audit before public use.
Evidence
What I worked on · Broker abstraction and operating controls, plus a refusal to report in-sample performance.
Caveat · Paper-trading validation only; backtests are historical simulations, not a real-money record.
Selected work
Each project explains why I started it, what I checked, and where the conclusion should stop.
Continue the conversation
Open to internship and entry-level roles near data analysis, financial and market research, fintech, strategy, BizOps, and service planning.