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

Our goal is to design a prediction and decision system for real-time use during a professional car race. In designing a knowledge discovery process for racing, we faced several challenges that were overcome only when domain knowledge of racing was carefully infused within statistical modeling techniques. In this article, we describe how we leveraged expert knowledge of the domain to produce a real-time decision system for tire changes within a race. Our forecasts have the potential to impact how racing teams can optimize strategy by making tire-change decisions to benefit their rank position. Our work significantly expands previous research on sports analytics, as it is the only work on analytical methods for within-race prediction and decision making for professional car racing.

[1]  John V. Guttag,et al.  A data-driven method for in-game decision making in MLB: when to pull a starting pitcher , 2013, KDD.

[2]  Mary E. Allender.  Predicting The Outcome Of NASCAR Races: The Role Of Driver Experience , 2011 .

[3]  Filippo Neri,et al.  Learning in the “Real World” , 1998, Machine Learning.

[4]  Leanne Streja.  Models for Motorcycle Grand Prix Racing , 2011 .

[5]  Craig A. Depken,et al.  Driver Success in the Nascar Sprint Cup Series: The Impact of Multi-Car Teams , 2009 .

[6]  Padhraic Smyth,et al.  From Data Mining to Knowledge Discovery in Databases , 1996, AI Mag..

[7]  Cynthia Rudin,et al.  Machine learning for science and society , 2013, Machine Learning.

[8]  Herbert A. Simon,et al.  Applications of machine learning and rule induction , 1995, CACM.

[9]  B. Skinner.  The Problem of Shot Selection in Basketball , 2011, PloS one.

[10]  Arthur E. Hoerl,et al.  Ridge Regression: Biased Estimation for Nonorthogonal Problems , 2000, Technometrics.

[11]  Inderpal S. Bhandari,et al.  Advanced Scout: Data Mining and Knowledge Discovery in NBA Data , 2004, Data Mining and Knowledge Discovery.

[12]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[13]  R. Tibshirani.  Regression Shrinkage and Selection via the Lasso , 1996 .

[14]  Hsinchun Chen,et al.  Predictive Modeling for Sports and Gaming , 2010 .

[15]  David J. Hand,et al.  Deconstructing Statistical Questions , 1994 .

[16]  John V. Guttag,et al.  Predicting the Next Pitch , 2012 .

[17]  Carla E. Brodley,et al.  Applying classification algorithms in practice , 1997, Stat. Comput..

[18]  E. H. Simpson,et al.  The Interpretation of Interaction in Contingency Tables , 1951 .

[19]  Usama M. Fayyad,et al.  Knowledge Discovery in Databases: An Overview , 1997, ILP.

[20]  Ron Kohavi,et al.  Guest Editors' Introduction: On Applied Research in Machine Learning , 1998, Machine Learning.

[21]  Laks V. S. Lakshmanan,et al.  Auto-play: A Data Mining Approach to ODI Cricket Simulation and Prediction , 2014, SDM.

[22]  SISTER MARY CLARE.  All about WHO. , 1952, Hospital progress.

[23]  Michael Bailey,et al.  Predicting the Match Outcome in One Day International Cricket Matches, while the Game is in Progress. , 2006, Journal of sports science & medicine.

[24]  Alexander J. Smola,et al.  Support Vector Regression Machines , 1996, NIPS.