Skip to main content

Posts

Predicting BJJ Match Finishes & Points with Time-Series Forecasting

I was playing around with different types of data at work when I found an interesting article on the application of time-series forecasting to predict the future performance of sports players. Of course, I jumped at the opportunity to have fun with another data science tool and apply it to Brazilian Jiu Jitsu. What is Time-Series Forecasting? Time-series data is the collection of date and time intervals, usually in a sequential order. Time-series analysis explores how something changes over a period of time and extracts meaningful insights. Time-series forecasting takes historical data, like trends by the day, month, and year, and uses a machine learning model to predict future data points based on past performances. It takes into account seasonality patterns that occur at similar intervals. In the Jiu Jitsu world, there are clothing purchases right after someone gets promoted to a new belt or a spike in instructional video sales right after a fighter wins a big tournament. Bo
Recent posts

BJJ Scoreboard Analysis with Computer Vision

We’re back at it with a brand new Brazilian Jiu Jitsu data collection process to lend more insights into how matches were scored and trends at the 2019 World Championships. This time, we used computer vision techniques such as video event detection and optical character recognition to help us collect the points scored in matches and the exact time each score occurred. This blog is part of a larger project where my Crazy 88 teammate, Ashar Nadeem , and I are using a variety of data science tools to collect match data for BJJ. In this blog, we used 87 match videos posted on the International Brazilian Jiu Jitsu Federation YouTube channel from the 2019 World Championships. The matches included black belt male and female Quarterfinal, Semifinal, and Finals matches, arguably the most high stress and meaningful matches of the tournament. This portion of the project was limited to score detection—the points scored and the exact time a score happened—by analyzing a change in the number

Using Data Science to Create a Highlight Video For Jiu Jitsu

Before Maryland was quarantined due to the coronavirus, I was one week away from departing on a plane to California to compete in the 2020 IBJJF Pan Championships. I was also teeing up my next blog to predict the black belt outcomes using our Elo for BJJ model. Both of those plans were cancelled, but my search for more, quality data on our sport has not ceased. Data collection can be time consuming to get accurate, and I hope to have more for you all soon.  In the meantime, I created a short highlight video of one of my favorite matches from the 2019 IBJJF World Championships using data science. This is how I spend my free time while under lockdown, learning new skills. Process I turned to publicly available matches on the IBJJF's YouTube channel for show stoppers from last season. I've studied, and watched for entertainment, many of these videos with the extra time at home. Ultimately, I choose to analyze the finals match of the Heavy weight division between 2019 number

IBJJF Europeans Update - Elo Rating for BJJ

Here's a quick post-tournament update on our Elo Rating for BJJ . This post is an analysis of the statistical model, not the matches or fighters. Highlights:  We accurately predicted a few noteworthy first round matches with our Elo Rating system. Thalison Soares was slightly favored to win over Bruno Malfacine, with a win probability of 54.48%, and beat the long-time reigning Rooster weight world champ. Gabriel Sousa went up a weight class to Feather, but was still favored to win against Gianni Grippo, with a win probability of 65.64%.  Manuel Ribamar edged out Espen Mathiesen, with a win probability of 58.80%, and won his first European title. Italo Moura beat Gabriel Figueiro, with a win probability of 54.39%. We correctly predicted 20 first round match ups out of 24 matches, or 83% first round predictions (excluding no shows). Our Elo Rating for BJJ had a predictive accuracy of 72% overall.  We calculated the predictive accuracy by totaling the number of correc

Elo Rating for BJJ – A Predictive Model for Match Outcomes

In previous articles, I have looked at the new-ish IBJJF seeding system as a way to predict match outcomes at the IBJJF No Gi Pans . I used IBJJF medal results to rank fighters after the 2019 World Championships . I also created a machine learning model to help predict who will win a match up at the ADCC tournament . Today, we (yes a collab project between myself and Dan Tsinis ) are introducing the Elo Rating System for Brazilian Jiu Jitsu as a way to rank fighters and predict the probability of fighters winning in a potential match up. Below are the top 50 pound for pound competitors and the top 10-20 by each weight class. The ratings only include the last three years (2017-2019) and each year has a seasonal weight. This is not reflective of the best competitors of all time, but the most accurate of who competed the most in the last year. These are the current 2019 year-end standings. Predictions for First Round Matches at IBJJF Europeans 2020 With our Elo rating sys