Statistics & Data Science · UC Santa Barbara · Class of 2027

Turning data into
insight & action

I build statistical models, data pipelines, and interactive dashboards that help organizations understand what their data is saying.

R · Python R Shiny Tableau · Power BI Predictive Modeling NLP ArcGIS Git / GitHub
GitHub LinkedIn View Projects ↓

Selected Projects

Machine Learning · NLP · Python

Craving Recommendation System

A hybrid restaurant recommendation engine trained on 562,000+ Yelp reviews across 7,600 Philadelphia restaurants. Combines item-based collaborative filtering with content embeddings so users can describe cravings in plain language — "something warm and comforting" — and receive personalized results.

Collaborative FilteringText Embeddings sklearnpandasscipy.sparse
View on GitHub

EDA · Statistical Modeling · R

Post-Class 12 Dropout Risk Analysis

Investigated which factors — family income, parental education, or study habits — most predict dropout after India's Class 12 JEE exams. Used logistic regression and Welch's two-sample t-tests across a synthetic dataset of 5,000 students, with predicted probability visualizations in R.

Logistic RegressionWelch's t-test ggplot2ggeffectsQuarto
View Full Report

Policy Analysis · ArcGIS · Data Visualization

Richmond, Virginia's Housing Crisis

Examined investor-driven displacement, redlining legacy, and affordability collapse in Richmond — where home prices surged 52.6% in five years and eviction rates run nearly 3× the national average. Combined ArcGIS displacement mapping with Rosen-Roback economic analysis to propose data-backed policy interventions.

ArcGISPolicy Analysis Urban EconomicsData Storytelling
View Presentation

Research · Mixed Methods · R

INSPIRE — Peer Mentoring & Student Persistence

Longitudinal pre/post visualizations and change-score regression models examining how mentor trust and social capital predict shifts in student belonging and retention intent. Coded 600+ student reflections using the Gioia method; contributing to an ASEE conference paper integrating quantitative survey and qualitative data.

Longitudinal AnalysisChange-Score Regression Gioia Methodggplot2ASEE
View on GitHub

Experience & Skills

Undergraduate Research Assistant Mar 2026 – Present

UCSB College of Engineering · INSPIRE Group

Longitudinal visualizations and regression models on peer mentoring outcomes; Gioia qualitative coding of 600+ reflections; co-author on ASEE conference paper.

Analytics Assistant Feb 2026 – Present

UCSB Library · Collection Strategies Department

Automated data cleaning and reporting in R/Python; designed R Shiny and Tableau dashboards for collection usage and acquisition trends.

Financial Operations Systems Associate May 2024 – Present

Associated Students, UCSB

Implemented MIP/Microix Cloud financial system — workflow design, application configuration, and community rollout for A.S. financial operations.

CS & Statistics Learning Assistant Jul – Dec 2024

MAX Program, UCSB

Mentored first-year students transitioning to UCSB; facilitated study sessions for CS and Statistics coursework.

Languages

R Python

Tools & Platforms

R Shiny Tableau Power BI ArcGIS Excel Jupyter Notebook Git / GitHub Quarto

Methods

Predictive Modeling EDA Cross-Validation Data Cleaning & Visualization NLP Qualitative Coding Automated Pipelines

Relevant Coursework

Data Mining for Business AI in Industry Maps & Spatial Reasoning

Education

B.S. Statistics & Data Science UCSB · Class of 2027

Get in Touch

Open to data science internships, research opportunities, and interesting problems.

✉ annacha1144@gmail.com LinkedIn GitHub