Tire Changes, Fresh Air, and Yellow Flags: Challenges in Predictive Analytics for Professional Racing

Tulabandhula, Theja; Rudin, Cynthia

doi:10.1089/big.2014.0018

Cited by 12 publications

(11 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The work done by Tulabandhula et al [34] comes closest to what is pursued in this paper. Using ML methods, they predict the change in position during the next outing (equal to a stint) in NASCAR races on the basis of the number of tires changed in the preceding pit stop.…”

Section: Motorsportmentioning

confidence: 69%

“…This is surprising, considering the amount of money and data in the sport. The work done by Tulabandhula et al [34] comes closest to our target. However, it is not applicable in our case, since their algorithm does not predict whether the driver should make a pit stop.…”

Section: Discussionmentioning

confidence: 80%

“…Support vector regression and LASSO performed best, reaching R 2 values of 0.4 to 0.5. It was found that "further reduction in RMSE, increase in R 2 , and increase in sign accuracy may not be possible because of the highly strategic and dynamic nature of racing" ( [34], p. 108). The work of Choo [35] is similar to that of Tulabandhula et al In recent seasons, Amazon [36] applied ML techniques to provide new insights into F1 races for fans.…”

Section: Motorsportmentioning

confidence: 99%

See 2 more Smart Citations

Virtual Strategy Engineer: Using Artificial Neural Networks for Making Race Strategy Decisions in Circuit Motorsport

et al. 2020

View full text Add to dashboard Cite

In circuit motorsport, race strategy helps to finish the race in the best possible position by optimally determining the pit stops. Depending on the racing series, pit stops are needed to replace worn-out tires, refuel the car, change drivers, or repair the car. Assuming a race without opponents and considering only tire degradation, the optimal race strategy can be determined by solving a quadratic optimization problem, as shown in the paper. In high-class motorsport, however, this simplified approach is not sufficient. There, comprehensive race simulations are used to evaluate the outcome of different strategic options. The published race simulations require the user to specify the expected strategies of all race participants manually. In such simulations, it is therefore desirable to automate the strategy decisions, for better handling and greater realism. It is against this background that we present a virtual strategy engineer (VSE) based on two artificial neural networks. Since our research is focused on the Formula 1 racing series, the VSE decides whether a driver should make a pit stop and which tire compound to fit. Its training is based on timing data of the six seasons from 2014 to 2019. The results show that the VSE makes reasonable decisions and reacts to the particular race situation. The integration of the VSE into a race simulation is presented, and the effects are analyzed in an example race.

show abstract

Section: Motorsportmentioning

confidence: 69%

Section: Discussionmentioning

confidence: 80%

Section: Motorsportmentioning

confidence: 99%

See 1 more Smart Citation

Virtual Strategy Engineer: Using Artificial Neural Networks for Making Race Strategy Decisions in Circuit Motorsport

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Deep learning-based forecasting has observed its success across domains, including: demand prediction [20], traffic prediction [21], clinical state progression prediction [25], epidemic forecasting [8], etc. However, when addressing the forecasting problem in the specific domain of motorsports, we found that the state-of-the-art models in this field are simulation methods or machine learning methods, all highly rely on the domain knowledge [1], [12], [17], [30]. Simply applying a deep learning model here does not deliver better forecasting performance.…”

Section: Introductionmentioning

confidence: 99%

Rank Position Forecasting in Car Racing

Peng¹,

Li²,

Akkas³

et al. 2020

Preprint

View full text Add to dashboard Cite

Rank position forecasting in car racing is a challenging problem, which is featured with highly complex global dependency among the cars, with uncertainty resulted from existing exogenous factors, and as a sparse data problem. Existing methods, including statistical models, machine learning regression models, and several state-of-the-art deep forecasting models all perform not well on this problem. By elaborative analysis of pit stops events, we find it is critical to decompose the cause effects and model them, the rank position and pit stop events, separately. In the choice of sub-model from different deep models, we find the model with weak assumptions on the global dependency structure performs the best. Based on these observations, we propose RankNet, a combination of encoderdecoder network and separate MLP network that capable of delivering probabilistic forecasting to model the pit stop events and rank position in car racing. Further with the help of feature optimizations, RankNet demonstrates a significant performance improvement over the baselines, e.g., MAE improves more than 10% consistently, and is also more stable when adapting to unseen new data. Details of model optimization, performance profiling are presented. It is promising to provide useful forecasting tools for the car racing analysis and shine a light on solutions to similar challenging issues in general forecasting problems.

show abstract

“…It is very much similar to our work-flow, where they used the combination of previous data and in game data to predict a pitchers performance. Tulabandhula and Rudin (2014) were designed a real time prediction and decision system for professional car racing. Model makes the decision of when is the best time for tire change and how many of them.…”

Section: Introductionmentioning

confidence: 99%

Predicting Outcome of Live Cricket Match Using Duckworth- Lewis Par Score

Shah¹

2017

IJSSAM

View full text Add to dashboard Cite

Cricket is the second most watched sport in the world after soccer, and enjoys a multi-million dollar industry.There is remarkable interest in simulating cricket and more importantly in predicting the outcome of cricket match which is played in three formats namely test match, one day international and T20 match. The complex rules prevailing in the game, along with the various natural parameters affecting the outcome of a cricket match present significant challenges for accurate prediction. Several diverse parameters, including but not limited to cricketing skills and performances, match venues and even weather conditions can significantly affect the outcome of a game. There are number of research paper on pre-match prediction of cricket match. Many papers on building a prediction model that takes in historical match data as well as the instantaneous state of a match, and predict match results. We know in the cricket match with shorter version match result keep on changing every ball. So, it is important to predict the outcome of the match on every ball. In this paper, I have developed a model that predicts match result on every ball played. Using Duckworth-Lewis formula match outcome will be predicted for live match. For every ball bowled a probability is calculated and probability figure is plotted. For betting industry this model and the probability figure will be very useful for bettor in deciding which team to on and how much to bet.

show abstract

Tire Changes, Fresh Air, and Yellow Flags: Challenges in Predictive Analytics for Professional Racing

Cited by 12 publications

References 17 publications

Virtual Strategy Engineer: Using Artificial Neural Networks for Making Race Strategy Decisions in Circuit Motorsport

Virtual Strategy Engineer: Using Artificial Neural Networks for Making Race Strategy Decisions in Circuit Motorsport

Rank Position Forecasting in Car Racing

Predicting Outcome of Live Cricket Match Using Duckworth- Lewis Par Score

Contact Info

Product

Resources

About