Heart Stroke Risk Prediction
Machine learning model to predict stroke risk from healthcare data, with preprocessing, training, and an interactive Streamlit app.
Python, scikit-learn, Streamlit
UC Davis Graduate | B.S. Statistical Data Science, Minor in Computer Science
Currently: Seeking full-time Data Analyst / Data Engineer roles while building an SF Restaurant Safety Map.
Email: royho.career@gmail.com
Location: Davis, CA | San Francisco, CA
About
Hi, my name is Roy Ho, and I am a recent UC Davis graduate with a Bachelor's degree in Statistical Data Science and a minor in Computer Science.
I'm interested in building data-driven solutions using Python, R, SQL, and Excel, with a focus on machine learning. I'm currently pursuing roles in data analytics and data engineering.
11+
Projects
8+
Core Tools
25
Page AI Research Paper
Core Skills
- Python
- SQL
- Excel
- R
- Pandas
- Scikit-learn
- Data Visualization
- Machine Learning
SF Restaurant Safety Map
Built an interactive map of 5,500+ San Francisco restaurant health inspections using public DataSF data, an ETL pipeline into a SQLite schema, a Flask REST API, and a React + Mapbox frontend for search, filters, and inspection details.
Python, SQL, Flask, React, Mapbox, ETL
GitHubJob Analytics Dashboard
Built a dashboard to analyze job market trends, including salaries, skills, and geographic differences across roles.
Python, Data Visualization
GitHubDrowsy Driver Detection
Built a real-time drowsiness detection system using computer vision techniques and a CNN model trained on eye-state data.
Python, OpenCV, CNN
GitHubPortuguese Wine Type and Quality Prediction
Classified red vs. white wines and predicted quality ratings using logistic regression, LDA, and PCA on chemical properties.
Python, scikit-learn, PCA
Stock Trading Algorithm
Built a multi-factor stock screening model with NLP sentiment analysis (FinBERT), supervised classification, and an automated daily ETL pipeline delivering real-time investment signals.
Python, scikit-learn, NLP, ETL
NBA Player Performance Prediction
Predicted 5th-season NBA player performance using regression and classification models on historical stats and draft data.
Python, Random Forest, Gradient Boosting
Analyzing Movie Reviews Across Genres
Scraped and compared IMDb audience reviews with professional critic reviews using sentiment analysis and NLP models.
Python, Selenium, VADER, RoBERTa
Drake Time Series Analysis
Forecasted Drake's popularity trends using 14 years of Google Trends data with ARMA and ARIMA models.
R, forecast, ggplot2
NBA Player Salary Analysis
Analyzed the relationship between player performance metrics and salary structures using regression and clustering.
R, tidyverse, ggplot2
Socioeconomic Predictors of Crime Rates
Modeled the relationship between poverty, unemployment, and crime rates using multiple linear regression and model selection.
R, ANOVA, AIC/BIC
Graph-Based Shortest Path Analysis (Six Degrees of Kevin Bacon)
Built a graph traversal algorithm to compute degrees of separation between actors through shared movie appearances.
Python, BFS, Graph Algorithms
Experience
JAIKE
Journal of Artificial Intelligence and Knowledge Engineering
January 2025 – Present
Artificial Intelligence Researcher
- Conducted research on LLM-based automation, focusing on API-driven system design, agent orchestration frameworks, and productivity applications across research, coding, and enterprise workflows.
- Authored a 25-page research paper on LLM-based automation and agent architectures, synthesizing peer-reviewed and industry research on API integration, architectural design patterns, system limitations, and responsible deployment; submitted for journal publication.
- Served as a peer reviewer for JAIKE, evaluating research on retrieval methods in large language models, reasoning performance in extended tasks, and large-scale model architectures for methodological rigor and evaluation quality.
TechSprint Innovators
March 2024 – September 2025
Head of Data Engineering
- Built a multi-factor stock screening model using fundamental, technical, and NLP-based sentiment features (FinBERT).
- Developed and evaluated a supervised classification model in scikit-learn to predict price appreciation, performing feature selection, model tuning, and performance validation on historical market data.
- Engineered and automated a daily ETL data pipeline (Python, yfinance, Alpaca API) running on a Raspberry Pi to filter equities, generate structured CSV outputs, and deliver real-time investment signals via Discord webhook.
Let's Connect!
Resume
View or download a PDF of my experience, education, and skills.
Preview
Hobbies
Outside of work, I enjoy thrifting, bass fishing, spending time outdoors, and playing poker. I also love keeping up with fashion and music.
