Batikas, MichailHettmann, Valentin Fedor2024-11-132024-11-132024-01-112024-01-11http://hdl.handle.net/10362/175111This thesis explores Formula 1 pit stop strategies through advanced analytics, with a focus on driver clustering in relation to performance, tactical, and behavioural aspects. Our approach led to the identification of four distinct driver categories, providing a framework to investigate various pit stop strategies. By integrating these driver profiles into predictive models, the study delves into the impact of driver characteristics on team strategy and pit stop efficiency. We introduce a novel dimension by developing a binary prediction model for pit stop timing, thoroughly evaluated within a simulation environment. This research contributes to a more refined understanding of strategic elements in Formula 1, demonstrating the role of tailored analytic methods in optimizing racing tactics and decision-making processes.engMachine learningPredictive modelingStrategyPit stopMotorsportFormula 1master thesis203605616