Daily Fantasy Sports have been studied intensively by academics from various elds due to the game's nature within the area of skill and gambling. Despite numerous approaches to investigate its principles and mechanisms by creating predictive models, there is a lack of extensive analyses in hindsight to lineup creation as well as evaluations for real-life scenarios. By scraping and melting data from various sources including historic odds, weather information and player attributes from video-games, a Stacked Ensemblemodel has been trained using R/H2o. Subsequently, multiple strategies commonly used by punters have been dened and run in simulations against each other; allowing for assumptions whether fantasy football games could be beatable despite of the rake by following certain approaches. In contrast to existing literature, results provide insights into performances of strategies in regards to various tournament types, showing signicant dierences in mean fantasy points. In conclusion, new approaches for improvements are presented.
Masterprüfung mit Defensio, Selig David
06.11.2018 10:00 - 11:30
Organiser:
SPL 5
Location:
Besprechungsraum 4.34
Währinger Straße 29
1090 Wien
1090 Wien