top of page
CertificateBackground.png

Certificate of Completion

ErdosHorizontal.png

THIS ACKNOWLEDGES THAT

HAS COMPLETED THE SPRING 2024 DATA SCIENCE BOOT CAMP

Andrei Prokhorov

clear.png

Roman Holowinsky, PhD

MAY 01, 2024

DIRECTOR

DATE

TEAM

Muscle Metrics: Revolutionizing Bodybuilding Competitions with Elo Ratings

Jessica De Silva, Andrei Prokhorov

clear.png

We developed a predictive metric for professional bodybuilding competitions, enabling accurate forecasts of the resulting rankings of competitors. This metric-based ranking serves as an alternative to the traditional alphabetical grouping during competition pre-judging. Bodybuilding competition data is collected using BeautifulSoup from the NPC News Online website. Competitors are assigned a numerical value based on their competition history using the Elo rating model. After each competition, their Elo ratings are adjusted based on the Elo ratings of competitors they outranked and those who outranked them. From the Elo ratings, we can predict the outcomes of upcoming competitions. The results indicate that predicted competition outcomes using Elo ratings significantly outperform alphabetical ordering, suggesting that metric-based ranking is a more effective method for initial competitor grouping.

Screen Shot 2022-06-03 at 11.31.35 AM.png
github URL
bottom of page