NORMA eResearch @NCI Library

Sports Analytics: Analysis of the National Football League

Gorman, Daniel (2017) Sports Analytics: Analysis of the National Football League. Undergraduate thesis, Dublin, National College of Ireland.

[thumbnail of Bachelor of Science]
PDF (Bachelor of Science)
Download (2MB) | Preview


The initial plan to implement this research project came from a talk during 3rd-year work placement module where students were invited to hear about the different streams that will be on offer for 4th-year students. Following up the analytics stream with lecturers at the beginning of the semester statistics was the most appealing option with the combination of statistics and sports, it became an fascinating idea for the research project. It was also the perfect opportunity to undertake a project in a fast-growing area of Sports Analytics. Teams in almost every sport have an analytics department now, examples; Bayern Munich (Football), Golden State Warriors (Basketball) and Oakland Athletics (Baseball). National Football League franchises and followers of the sport have been relatively slow integrating useful analytical techniques to the sport. Research of the NFL resulted in numerous research papers discussing the lack of analytical measures to analyse players in the sport pales in comparison to other sports when analytics is involved. In other sports, i.e. Baseball and Basketball it has been easier to quantify and analyze the data in such sports and put a value on player’s importance to a team but not so much with American football (Gabler, 2017), with the vast number of variables contained in just one play. The Shane Battier case study (Widjaya, 2015) which former National Basketball Association (NBA) player Shane Battier talks about how big data made him a better player overall by understanding his strengths in different scenarios and positions on the court.

Analytics has not fully taken off yet within the NFL community, with so many more variables and outcomes than other sports. Encapsulating a correct data mining approach to the sport is hard. So, therefore this research report will aim to improve the analytical strategy within American Football

The objectives of the project are to provide an exploratory analysis of the return on investment (ROI) in players, ROI will have various factors, e.g. Contract length/value, snaps played, first downs, yards gained (offensive players). These are just some of the factors that will be used to calculate the ROI of a player to a team. The aim is to build a regression model based on the play-by-play data from the 2014 season.

Item Type: Thesis (Undergraduate)
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
Q Science > QA Mathematics > Computer software
T Technology > T Technology (General) > Information Technology > Computer software
Divisions: School of Computing > Bachelor of Science (Honours) in Computing
Depositing User: Caoimhe Ní Mhaicín
Date Deposited: 26 Oct 2017 18:01
Last Modified: 26 Oct 2017 18:04

Actions (login required)

View Item View Item