Beginners

The 4 Types of Sports Analytics Projects

Projects are one of the most actionable things you can do to break into sports analytics. Projects show teams and organizations the quality of work that you produce and can give them an immediate reason to hire you.

In this post, I break down the types of sports analytics projects that are out there. Sometimes the hardest thing to do is get started, and this should give you a concrete idea about the destination you want to reach. From there, you can develop the relevant questions and analysis techniques.

Types of Sports Analytics Projects

  1. Projecting outcomes – You are trying to project how players or teams will perform by game or by season in this project type. Most of these applications are relevant for the sports gambling context. However, they can also be useful for individual sports teams. An example of this would be if you are trying to calculate what the spread should be on each basketball game this year. You could use that to potentially bet on outcomes.
  2. Valuing players or teams – Related to the projecting outcomes, sometimes we want to understand if a player is worth the investment in the draft or on the trade market. Trying to understand how certain attributes impact the value of a player can be instrumental to sports teams. An example would be if you were to look at physical data of running backs to determine if that had a measurable impact on how often they fumble the ball. A project like this could have a tremendous impact on how organizations draft players.
  3. Identifying areas of improvement – Sometimes the numbers reveal things that the coaches and players don’t see. An example of this has been the shift in value of on base percentage in baseball. Analysis can suggest that if a player takes more pitches or a pitcher changes the pitches that they throw, perhaps they can improve their performance. Similar to this, when to challenge penalties or when to call timeouts can also have interesting and actionable outcomes for teams.
  4. Understanding the game – Sometimes we want to understand how the game has changed. An example of this would be Beyond the Arch. Brennan clustered players based on the types of plays they are part of over time. We can see the new types of players as well as how players have changed over time. This can give the casual viewer insight into changes in the game and perhaps have an impact on how coaches use players or trade for others.

I am sure that there are other types of projects that I have overlooked, but framing yours in one of these ways can help you cut through the noise.

Ken Jee

Ken is one of the founders of Playing Numbers. He has worked in sports analytics for the last 5 years focusing primarily on golf and basketball. He founded playing numbers to help others learn about the field he loves.

Recent Posts

Sports Analytics & Streaming Data Science on Twitch

In this video, I had the pleasure of speaking with Nick Wan. Nick streams data…

3 years ago

Classifying MLB Hit Outcomes

In 2015, MLB introduced Statcast to all 30 stadiums. This system monitors player and ball movement and…

4 years ago

Data Science in Sports (Talk at Northwestern University)

This past weekend, I was honored to speak to almost 100 Kellogg MBA students about…

4 years ago

Jimmy Graham: A risk worth taking for the Chicago Bears?

Bears fans got a lesson in regression to the mean last season. It may have…

4 years ago

Using ML to Understand Real Madrid’s Poor Last decade in La Liga

Using K-Means Clustering to analyze the types of teams Real Madrid and Barcelona drop points…

4 years ago

Using NCAA Stats to Predict NBA Draft Order

Intro & Lit Review Predicting the NBA draft is always difficult. Should you draft a…

4 years ago

This website uses cookies.