Nathan Kim — Statistics & Data Science

I. About

About me

I'm a Statistics & Data Science student at UC Santa Barbara, graduating in June 2026 with a Technology Management Certification. I am drawn to transforming complex systems into interpretable insights, revealing patterns that inform meaningful decisions.

Right now I'm a data science intern at BlueAlpha, building synthetic data generators and benchmarking workflows for Marketing Mix Modeling. Before that I spent eight months at NCEAS designing reproducible pipelines for biodiversity data. On the side, I build agentic AI projects, most recently Romus, a real-time computer vision form coach, and Dialed, a multi-agent guardrail layer for social media.

Outside of code, you will find me reading books, going on runs, exploring nature, or spending time with family and friends.

II. Experience

Where I've worked

Data Science Intern @ BlueAlpha
San Francisco, CA
Jan 2026 — Present
- Built a synthetic marketing data generator that produces realistic Marketing Mix Modeling (MMM) datasets with configurable ground-truth parameters — ROI, adstock decay, and channel saturation effects.
- Implemented statistical and time-series simulation frameworks that emit weekly marketing data with seasonality, stochastic noise, and realistic channel-level spend patterns across digital ad platforms.
- Stress-tested MMM models against the synthetic datasets, comparing recovered parameters against known ground truth to benchmark attribution accuracy under controlled conditions.
- Designed benchmarking workflows to evaluate how reliably MMM models recover causal channel contributions across simulated marketing environments.
Data Science Intern @ National Center for Ecological Analysis and Synthesis
Santa Barbara, CA
Jul 2025 — Mar 2026
- Designed reproducible R-based data pipelines that automated formatting and ingestion of large-scale biodiversity datasets for long-term conservation research.
- Cleaned and standardized 50k+ heterogeneous vegetation records, enabling accurate ecological modeling and seamless integration into VegBank, a national open-access plant community database.
- Performed exploratory data analysis on large-scale vegetation datasets to surface data quality issues, find patterns, and inform downstream spatial analysis and ML modeling.
- Worked with ecological scientists and data managers to align variable formats with metadata standards and prep datasets for predictive modeling, public release, and cross-study comparison.

III. Projects

Things I've built

A handful of products and experiments. Click any project for the longer story.

Romus.

2026

Real-time computer-vision coach for weightlifting form.

A real-time pose-tracking system that grades weightlifting form on the fly and gives personalized voice cues mid-set.

★ BroncoHacks 2026 Winner

LivePythonFastAPIMediaPipeWebSocketsClaudeRAGComputer VisionAI

Dialed.

2026

AI guardrails against manipulative social-media content, in real time.

A multi-agent system that watches your social feeds and intervenes when it detects manipulative patterns.

★ 2x BeachHacks 9.0 Winner

LivePythonFastAPIFetch.aiSupabaseWebSocketsBrowser-useElevenLabsAI

Investment Performance Tracker.

2025

ARIMA-based forecasting and risk dashboard for portfolios in R Shiny.

A customizable time-series forecasting pipeline with conservative and aggressive modes, plus an interactive Shiny dashboard for risk and return analysis.

LiveRShinyARIMATime SeriesFinance

IV. Connect

Let's get in touch

Best way to reach me is over email. I'm also on GitHub and LinkedIn.

nathank0306@gmail.com

GitHub

@nakim12

in/kim-a-nathan

Nathan Kim.