Austin Stephen

Fatigue in the NBA
Organization(s): Carnegie Mellon University & The Atlanta Hawks
Language(s): R

For summer 2021, I was a member of a 15 person cohort in an REU at Carnegie Mellon University. In this program, students work on applied projects in statistics and data science through the lens of sports analytics.
Advised by Max Horowitz at the Atlanta Hawks, my team researched the influence of player fatigue on game outcomes. We used R for scraping in-game tracking data (credit the NBAr package) and aggregated over 300 variables about players on a game by game level for a decade worth of games. We found the narrative portrayed by sports media is often inaccurate, substantial evidence players achieve a high degree of recovery between games, and offered a framework for isolating factors that contribute to game outcomes.

A link to the paper will be available once we complete the publication process.

CMSAC Project Showcase
AI Index
Organization(s): Stanford University & University of Wyoming
Language(s): Bash, R

Every year the HAI lab at Stanford and partners release a report tracking and summarizing progress in AI. I ran a set of computational experiments using the high-performance computing cluster at the University of Wyoming examing the improvements in Boolean Satisfiability solvers over the last 5 years. My experiments are inclueded and I am cited on page 72.

Press Release: Press Release
Full Report(pg. 72): 2021 AI Index
Automated Algorithm Selection
Organization(s): University of Wyoming
Language(s): Bash, R, Python

In the MALLET lab I worked on a project improving automated algorithm selection. Traditionally, automated algorithm selection models are trained on the problem instance feature values and performance data from algorithm runs. The project I work on showed training these automated algorithm selection models on the feature values of the algorithms in addition to problem instance features improves overall performance. This allows the evaluation of sets of problem instances in less time and with less memory by choosing the most optimal algorithm more frequently.

An extended abstract on my work submitted to AAAI the Undergraduate Consortium. Abstract.pdf

2020 Wyoming Research Scholars Virtual Symposium
Cross-Country Optimization
Organization(s): none
Languages(s): R

I've been an avid runner for nearly a decade now and my brother currently runs for a collegiate cross-country and track program. One day we were discussing the NCAA national meet when I realized the way cross-country meets are scored means leaves room for optimization. The closer a runner is to the median of the field the same percentage improvement in their time has a greater positive impact on their team's score. I set out to model and visualize this relationship in R. Check out the graphic below I made using ggplot to get a visual sense for why this is the case. I ultimately created a script that returns the runners on a team in order of how relevant their improvements are to the team score. See the pdf below for the full write up on this project.

The full report. Cross-country.pdf
Complete the Maze
Organization(s): University of Wyoming
Languages(s): Java

For COSC 3011, as part of a 4-person team, I wrote a complete the maze game. The game consists of a GUI, timing system, reading and writing to binary files in order to store and retrieve the state of the game, and the ability for users to upload their own mazes. The project was an exercise in the implementation of concepts that increase the robustness of large software systems. Also, it was accompanied by changes in requirements throughout the development process to challenge teams use of encapsulation and extendability.

The code is available at this githib repo:
link