Quantifying the Outfield Shift Using K-Means Clustering

  • Jeffrey Gerlica
  • Izaiah LaDuke
  • Garrett O’Shea
  • Pierce Pluemer
  • John Dulin
Keywords: Baseball, Sabermetrics, Defensive Shifting, K-Means Clustering

Abstract

Sports teams constantly search for a competitive advantage (e.g. bidding for free agents or scouting nontraditional markets). As popularized by Moneyball, we focus on advanced analytics in baseball. These sabermetrics are employed to provide objective information to management and coaches to support player management and in-game strategy decisions. Though widely used at the professional level, analytics use in college baseball is limited. Air Force Academy Baseball has been one win short of qualifying for the Mountain West tournament three straight years, resulting in the loss of potential income from media payouts and exposure for future recruiting efforts. Using a K-means clustering method for defensive shifting, we calculate an overall catch probability increase of 7.4% with a shifted outfield in a one-game case study. Based on our analysis, we provide evidence that Air Force Baseball can benefit from an outfield defensive shifting scheme that drives a competitive advantage and additional wins.

References

Baumer, B. (2014). An Overview of Current Sabermetric Thought II: Defense, WAR, and Strategy. The Sabermetric Revolution. (pp. 57–84).
Becker, K. W. (2009). Optimizing Defensive Alignments in Baseball through Integer Programming and Simulation. Kanas State University. Retrieved from https://krex.k-state.edu/dspace/handle/2097/2345?show=full.
Beneventano, P., Berger, P.D., & Weinberg, B.D. (2012). Predicting Run Production and Run Prevention in Baseball: The Impact of Sabermetrics. International Journal of Business, Humanities and Technology. 2(4), 67-75.
Hawke, C. J. (2017). Quantifying the Effect of the Shift in Major League Baseball. In Kansas State Senior Projects. Spring 2017. 191. Retrieved from http://digitalcommons.bard.edu/senproj_s2017/191.
Helfand, Z. (2015, July 19). Use of Defensive Shifts in Baseball is Spreading - because it works. Retrieved October 21, 2019, from https://www.latimes.com/sports/la-sp-baseball-defensive-shifts-20150719-story.html.
James, G., Witten, D., Hastie, T., & Tibshirani, R. (2017). An Introduction to Statistical Learning: with applications in R. New York: Springer.
Lewis, M. & Bailey, R. (2015). Batted Ball Spray Charts: a system to determine infield shifting. In 2015 Systems and Information Engineering Design Symposium, 206-211.
MLB Advanced Media. (n.d.). Catch Probability. Retrieved from http://m.mlb.com/glossary/statcast/catch-probability
Pankin, M.D. (1978). Evaluating Offensive Performance in Baseball. Operations Research. 26(4), 610-619.
Valero S. (2016). Predicting Win-Loss outcomes in MLB regular season games – A comparative study using data mining methods. International Journal of Computer Science in Sport, 15(2), 91-112.
Published
2021-03-06