Figure - available from: Journal of Quantitative Analysis in Sports
This content is subject to copyright. Terms and conditions apply.
Source publication
Successful performance in Formula One is determined by combination of both the driver’s skill and race-car constructor advantage. This makes key performance questions in the sport difficult to answer. For example, who is the best Formula One driver, which is the best constructor, and what is their relative contribution to success? In this paper, we...
Citations
... Beyond strategy optimization, researchers have also focused on understanding the relative contributions of driver skill and car performance. Van Kesteren and Bergkamp [8] used Bayesian analysis to disentangle driver skill and constructor advantage in F1 race results, finding that the car (constructor) is a significantly larger factor than the driver. Bonomi et al. [10] employed a custom Genetic Algorithm for strategy optimization, demonstrating the strength of this approach. ...
Formula One race strategy optimization has traditionally relied on predefined heuristics and Monte Carlo simulations, which are computationally expensive and lack adaptability to live race conditions. While prior works have explored reinforcement learning (RL) in other motorsport categories, its application to Formula One strategy remains underdeveloped. This research introduces a reinforcement learning framework aimed at dynamically predicting tire compound choices after the summer break, addressing the gap in adaptive decision-making for in-race strategic planning. The proposed RL model employs a deep recurrent Q-network (DRQN) trained using a Monte Carlo race simulator. The state space incorporates critical race parameters such as tire degradation, gaps to competitors, and race progress, while the action space consists of tire compound selection and pit stop timing. A reward function, balancing immediate lap performance and long-term finishing position, guides the learning process. The model is further enhanced with explainability techniques, including feature importance analysis and decision tree-based surrogate models, to improve transparency and trust in automated strategy recommendations.
... A novel Bayesian multilevel rank-ordered logit regression method to model individual race finishing positions was presented [Van Kesteren and Bergkamp 2023], allowing inferences about driver skill and constructor advantage. ...
This paper presents a network analysis to recognize the most important Formula One drivers, focusing on podium finishes as a metric of influence. We investigated a dataset comprising 855 drivers, 1,079 races, and 25,840 results to explore the relationships and performance dynamics among drivers. The use of centrality measures and community detection in network analysis offers a novel approach to evaluating Formula One drivers, beyond traditional metrics like championship or race wins. In our comprehensive analysis, it was determined that PageRank yielded the most insightful results, effectively capturing the essential contributions and setting a new benchmark for assessing excellence in Formula One racing and other sports.
... In Formula 1 races, the technical regulation often revises a little if a major regulation change is not made. As a result, the training data for the network are all from 2014 onwards, which is considered the beginning of the "Hybrid Era" of Formula 1 [8]. Moreover, only the qualifying fastest lap times are included because the result of a qualifying session is only related to the fastest lap which every driver can achieve. ...
Making comparisons and analyzing players in the sporting world is extremely valuable. The media, coaching staff, and players all rely on this data to assess performance, develop strategies, and make critical decisions. Therefore, neural networks can be employed to create a practical system that uses previous years data to predict future performance. This paper uses a Deep Neural Network (DNN) to predict the fastest lap time in qualifying for Formula 1 (F1) races. The network categorizes data to learn each drivers performance at each circuit and provides separate predictions. By doing so, it considers the unique characteristics of each driver and track, enabling more accurate predictions. The paper demonstrates that neural networks tend to have better performance and adaptability in such complex environments compared to traditional mathematical methods like linear regression. Neural networks can learn from the data and detect patterns that are difficult to capture with traditional methods. As a result, they can achieve a relatively precise prediction, providing valuable insights and decision-making support for coaches, drivers, and fans.
... Modelling Formula (1) races is an interesting econometric problem (Bell et al., 2016;van Kesteren and Bergkamp, 2023) of significant wider interest (Maurya, 2021). It is of interest to separate out driverlevel and car-level effects. ...
... It is of interest to separate out driverlevel and car-level effects. Previously, such an analysis has only been possible over longer time periods (Bell et al., 2016;Eichenberger and Stadelmann, 2009;van Kesteren and Bergkamp, 2023). Here, we present a solution that requires only one season of previous data. ...
... Comparing drivers in this way suggests two drivers Max Verstappen (Red Bull) and Fernando Alonso (Aston Martin) outperform their respective cars. Past academic research has previously highlighted Verstappen's level of performance as historically significant (van Kesteren and Bergkamp, 2023). ...
This paper explored the potentiality of social networks analysis to discuss the industrial organization of Formula One since the 2000 season. We tested three major hypotheses related to the centrality of championship teams, their selectiveness when observing drivers’ moves, and the role of certain explicative attributes. There are oligopolistic elements in Formula One, with champions adopting high values of betweenness centrality, sending and receiving drivers from some other teams and opting to exchange drivers and resources from other teams with not-so-competitive scuderias. Formula One teams that win the Constructors’ Championship tend to assume central roles in the network of drivers’ moves. Despite their centrality, these winning teams are very selective regarding the origin of the drivers they want to contract. There are more chances of contractual ties between teams which are not significantly close in terms of ranks or budgets.
Neural networks are widely used due to the adaptability of models to many problems and high efficiency. These solutions are also gaining popularity in the design of Decision Support Systems. It leads to increased use of such techniques to support the decision-maker in practical problems.
In this paper, we propose an Artificial Neural Network Decision Support System (ANN-DSS) based on Multilayer Perceptron. The model structure was determined by searching the optimal hyperparameters with Tree-structured Parzen Estimator. Based on the qualification results, the proposed system was directed to evaluate the Formula 1 divers’ best lap time during the race. Obtained rankings were compared with reference rankings using the WS rank similarity. Model performance proves to be highly consistent in rankings predictions, which makes it a reliable tool for the given problem.
