What Makes a National Football League Team Successful? an Analysis of Play by Play Data

Abstract

The National Football League (NFL) is one of the most popular sports in North America. The league showcases many strong athletes and winning is very important to all teams; however, for every winning team, there is a losing team, and it is the coaches' responsibility to decide what plays to call in order to help their teams win. Data mining play data can help show trends and areas where the top teams in the NFL excel by looking at questions like how often certain plays are run, how many yards do the plays get and where on the field are touchdown scored. With the help of data mining intelligent tools such as Naive Bayes, decision tree algorithms and association rules, we worked to isolate the areas where the best teams in the league separate themselves and produce winning franchises. By classifying the teams into two categories - the top teams and bottom teams - we were able to compare the two classes for differences which explain what results in more success in the league. Although we found that most teams - both top and bottom teams - use similar plays, there were also factors that distinguished the two types of teams. This research highlights these specific factors and some overall distinctions found between the more successful versus less successful teams to the NFL community.