In this paper we present a model to predict player performance in fantasy football. In particular, identifying high-performance players can prove to be a difficult problem, as there are on occasion players capable of high performance whose past metrics give no indication of this capacity. These "sleepers"' are often undervalued, and the acquisition of such players can have notable impact on a fantasy football team's overall performance. We constructed a regression model that accounts for players' past performance and athletic metrics to predict their future performance. The model we built performs favorably in predicting athlete performance in relation to other models, though this performance is heavily reliant upon the accuracy of estimates of athletes' workloads.
Morgan, Christopher D.; Rodriguez, Caroll; MacVittie, Korey; Slater, Robert; and Engels, Daniel W.
"Identifying Undervalued Players in Fantasy Football,"
SMU Data Science Review: Vol. 2
, Article 14.
Available at: https://scholar.smu.edu/datasciencereview/vol2/iss2/14
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial 4.0 License