Matthew Theisen

Data science and beyond

I'm Matt Theisen, a data scientist in the Greater Los Angeles area. I'm interested data science, conceptual modeling, and analytics. Here are some of my projects.

Featured Projects

Los Angeles Neighborhood Ranker: (Beta) An interactive web app which takes user-selected features to rank neighborhoods in Los Angeles.

Predictive Health Modeling: An interactive web app for predicting cancer survival. Results come from analyzing The Cancer Genome Atlas data for Acute Myeloid Leukemia.

Sun Calculator: A Python Flask-powered web application which estimates solar intensity using zip code and cloud forecasts. Provides visualizations with D3.js

Data science/statistics

Traversing The Cancer Genome Atlas: Ongoing project in which I use Python to parse, collect, and analyze data from The Cancer Genome Atlas.

Consumer Financial Protection Bureau Complaint Analysis: Shows how insights can come from data. Includes R code snippets showing the process of business problem formulation, data cleaning, statistical hypothesis testing and predictive algorithm implementation (randomForest package in R).

Jupyter Notebooks For Traffic Collision Analysis: Analysis of traffic collision data in Los Angeles County using Jupyter Notebook.

Video production/visual storytelling

Video production: Contest-winning videos I have produced/co-produced for video contests at UCLA.