top of page

TEAM

Predicting the Winners of Sumo Bouts

Kyla Pohl, siavash jafarizadeh, Ernesto Sandoval

clear.png

Sumo is one of the world's oldest sports and continues to thrive to this day. Two men make themselves as large as they possibly can in order to push, throw or smash their opponent out of the ring. It is also a sport with numerous data points that have been collected and maintained rigorously for many decades. As a fan of the sport, I thought it would be a fun exercise to create a program that takes in a pair of wrestlers and outputs the likelihood of each wrestler to win the bout. This program would take into account the previous outcomes of fights between the pair, the wrestlers' current standings in the tournament, their rank, their fighting style, their promotion-trajectory, etc. There is a dataset available on Kaggle with sumo information up to 2019, so we could start with this dataset before potentially scraping for the 2020-2024 data. Some data science areas that we could explore in creating this project could be Exploratory Data Analysis, feature engineering, predictive modeling, model evaluation, etc. I am new to data science and have a base level of Python understanding, so a lot of these topics would be new to me, but if anybody else is interested I think this could be a fun project that we could test against bouts in upcoming sumo tournaments!

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