This blog is meant to be a fun and unique take on predicting the 2019 MLB World Series winner. 

The 2019 Major League Baseball (MLB) playoffs have begun! Ever since Moneyball was published back in 2003, the popularity of sports analytics has soared beyond behind-the-scenes analytics teams to the general public, forever changing how people watch baseball. Anyone and everyone can leverage sports analytics data, especially for baseball where the data is plentiful. So, based on the data, who’s most likely to win the 2019 MLB World Series? I ran MLB data through DataRobot to find out. 

Methodology 

To predict who is most likely to win the World Series this year, DataRobot considered every MLB season dating back to 1980. Using Python, DataRobot calculated each team’s Elo rating as they entered the playoffs. Next, using the power of DataRobot’s automation, we built models to predict the winner of each playoff game based on each team’s Elo rating, additional advanced states (team’s OPS+, WAR (by position), RAA, etc.), and which team was playing at home.  After picking the best model, we simulated the 2019 MLB Playoffs 100,000 times to determine how often each team would win.

Results

Below is a list that ranks the top 10 MLB teams’ probabilities of winning the 2019 World Series:

Based on the data, the LA Dodgers and the Houston Astros have the highest chance of winning the 2019 World Series with about a 25% chance, with the New York Yankees in the number three spot. 

League Championships

The World Series is contested by the winners of the American League and National League Pennants. So, I took things a step further for this World Series prediction, and leveraged DataRobot to predict and rank the potential winners for both the American League and National League Pennants to help us understand not just who would win the World Series but how often each team in the playoffs would make it to the World Series. 

Below is a list ranking the top 5 MLB teams’ probabilities of winning the American League Pennant:

Based on the data, the Houston Astros have the highest chance of winning the 2019 American League Pennant at 40% and is in the lead by more than 15%. 

Below is a list that ranks the top 5 MLB teams’ probabilities of winning the National League Pennant:

Based on the data, the Los Angeles Dodgers have the highest chance of winning the 2019 National League Pennant at 47% and are in the lead by more than 20%.  

Data has proven to be very influential and valued throughout the sports world as seen with the US Open, Wimbledon, and March Madness. But, who’s to really know how the playoffs will go? The models we’ve built through DataRobot give us a better idea of how teams will fare this season, but there’s still plenty of room for surprises. This is what makes the world of sports analytics so exciting. 

About the Author:

Andrew Engel is General Manager for Sports and Gaming at DataRobot. He works with DataRobot customers across sports and casinos, including several Major League Baseball, National Basketball League and National Hockey League teams. He has been working as a data scientist and leading teams of data scientists for over ten years in a wide variety of domains from fraud prediction to marketing analytics. Andrew received his Ph.D. in Systems and Industrial Engineering with a focus on optimization and stochastic modeling. He has worked for Towson University, SAS Institute, the US Navy, Websense (now ForcePoint), Stics, and HP before joining DataRobot in February of 2016.

About the author

Andrew Engel

General Manager for Sports and Gaming, DataRobot

Andrew Engel is General Manager for Sports and Gaming at DataRobot. He works with DataRobot customers across sports and casinos, including several Major League Baseball, National Basketball League and National Hockey League teams. He has been working as a data scientist and leading teams of data scientists for over ten years in a wide variety of domains from fraud prediction to marketing analytics. Andrew received his Ph.D. in Systems and Industrial Engineering with a focus on optimization and stochastic modeling. He has worked for Towson University, SAS Institute, the US Navy, Websense (now ForcePoint), Stics, and HP before joining DataRobot in February of 2016.

Meet Andrew Engel