Where will the next ski injury occur? A system for visual and predictive analytics of ski injuries


Ski injury is a rare event with 2‰ rate (2 injuries per 1000 skier days expected). Additionally, injuries are dispersed over a ski resort spatially and temporally, making it harder to predict where the injury will occur. In order to inspect ski-related injuries, we have developed a visual system which allows global and spatial inspection of ski lift transportation RFID data. To enrich the visual environment, we have embedded a predictive lasso regression model which predicts injury occurrence spatially and temporally over a ski resort with an AUC performance of 0.766. We propose the model which allows decision makers to make real-time decisions on allocation of rescue service capacities at a ski resort. Predictive model improves the models existing in literature as it works for various locations at a ski resort, and makes predictions of occurring injuries on an hourly basis.

This is a preview of subscription content, log in to check access.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8


  1. Bohanec M, Delibašić B (2015, May) Data-mining and expert models for predicting injury risk in ski resorts. In: International conference on decision support system technology. Springer, Cham, pp 46–60

  2. Chang W, Cheng J, Allaire J, Xie Y, McPherson J (2015) Shiny: web application framework for R. R Package Version 0.11, 1

    Google Scholar 

  3. Cheng J, Xie Y (2016) leaflet: create interactive web maps with the JavaScript ‘Leaflet‘ library. R Package Version 1.0, 1

  4. Davis J, Goadrich M (2006, June) The relationship between precision-recall and ROC curves. In: Proceedings of the 23rd international conference on machine learning. ACM, pp 233–240

  5. Delibašić B, Marković P, Delias P, Obradović Z (2017a) Mining skier transportation patterns from ski resort lift usage data. IEEE Trans Human Mach Syst 47(3):417–422

    Article  Google Scholar 

  6. Delibašić B, Radovanović S, Jovanović M, Obradović Z, Suknović M (2017b) Ski injury predictive analytics from massive ski lift transportation data. Proc Inst Mech Eng Part P J Sports Eng Technol 232(3). https://doi.org/10.1177/1754337117728600

  7. Delibašić B, Radovanović S, Jovanović M, Vukićević M, Suknović M (2017c) An investigation of human trajectories in ski resorts. In: International conference on ICT innovations. Springer, Cham, pp 130–139

  8. D’Urso P, Massari R (2013) Fuzzy clustering of human activity patterns. Fuzzy Sets Syst 215:29–54

    Article  Google Scholar 

  9. Friedman J, Hastie T, Tibshirani R (2000) Additive logistic regression: a statistical view of boosting (with discussion and a rejoinder by the authors). Ann Stat 28(2):337–407

    Article  Google Scholar 

  10. Friedman J, Hastie T, Tibshirani R (2009) glmnet: Lasso and elastic-net regularized generalized linear models. R Package Version 1(4)

  11. Grosjean P, Ibanez F, Etienne M (2014) Pastecs: Package for analysis of space-time ecological series. R Package Version 1-3

  12. Hébert-Losier K, Holmberg HC (2013) What are the exercise-based injury prevention recommendations for recreational alpine skiing and snowboarding? Sports Med 43(5):355–366

    Article  Google Scholar 

  13. Hume PA, Lorimer AV, Griffiths PC, Carlson I, Lamont M (2015) Recreational snow-sports injury risk factors and countermeasures: a meta-analysis review and Haddon matrix evaluation. Sports Med 45(8):1175–1190

    Article  Google Scholar 

  14. James G, Witten D, Hastie T, Tibshirani R (2013) An introduction to statistical learning, vol 112. Springer, New York

    Google Scholar 

  15. Kalousis A, Prados J, Hilario M (2007) Stability of feature selection algorithms: a study on high-dimensional spaces. Knowl Inf Syst 12(1):95–116

    Article  Google Scholar 

  16. King MA, Abrahams AS, Ragsdale CT (2014) Ensemble methods for advanced skier days prediction. Expert Syst Appl 41(4):1176–1188

    Article  Google Scholar 

  17. Langran M, Selvaraj S (2004) Increased injury risk among first-day skiers, snowboarders, and skiboarders. Am J Sports Med 32(1):96–103

    Article  Google Scholar 

  18. Murray S (2017) Interactive data visualization for the web: an introduction to designing with. O’Reilly Media Inc, Sebastopol

    Google Scholar 

  19. Poulhès A, Mirial P (2017) Dynaski, an agent-based model to simulate skiers in a ski area. Procedia Comput Sci 109:84–91

    Article  Google Scholar 

  20. R Core Team (2014) R: A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna

  21. Raschner C, Platzer HP, Patterson C, Werner I, Huber R, Hildebrandt C (2012) The relationship between ACL injuries and physical fitness in young competitive ski racers: a 10-year longitudinal study. Br J Sports Med 46(15):1065–1071. https://doi.org/10.1136/bjsports-2012-091050

    Article  Google Scholar 

  22. Ruedl G, Philippe M, Sommersacher R, Dünnwald T, Kopp M, Burtscher M (2014) Current incidence of accidents on Austrian ski slopes. Sportverletzung Sportschaden: Organ der Gesellschaft fur Orthopadisch-Traumatologische Sportmedizin 28(4):183–187

    Article  Google Scholar 

  23. Ruedl G, Burtscher M, Wolf M, Ledochowski L, Bauer R, Benedetto KP, Kopp M (2015) Are self-reported risk-taking behavior and helmet use associated with injury causes among skiers and snowboarders? Scand J Med Sci Sports 25(1):125–130

    Article  Google Scholar 

  24. Schamel G (2012) Weekend vs. midweek stays: modelling hotel room rates in a small market. Int J Hosp Manag 31(4):1113–1118

    Article  Google Scholar 

  25. Schmitt KU, Hörterer N, Vogt M, Frey WO, Lorenzetti S (2016) Investigating physical fitness and race performance as determinants for the ACL injury risk in Alpine ski racing. BMC Sports Sci Med Rehabil 8(1):23

    Article  Google Scholar 

  26. Shi Q, Abdel-Aty M (2015) Big data applications in real-time traffic operation and safety monitoring and improvement on urban expressways. Transp Res Part C: Emerg Technol 58:380–394

    Article  Google Scholar 

  27. Tibshirani R (2011) Regression shrinkage and selection via the lasso: a retrospective. J R Stat Soc Ser B (Stat Methodol) 73(3):273–282

    Article  Google Scholar 

  28. Vanat L (2017) International report on snow and mountain tourism: overview of the key industry figures for ski resorts 2017. http://www.vanat.ch/RM-world-report-2017-vanat.pdf. Accessed 1 Jan 2019

  29. Venables WN, Ripley BD (2013) Modern applied statistics with S-PLUS. Springer, Berlin

    Google Scholar 

  30. Wei T, Simko V (2013) corrplot: Visualization of a correlation matrix. R Package Version 0.73 230(231):11

    Google Scholar 

  31. Wickham H (2016) ggplot2: Elegant graphics for data analysis. Springer, Berlin

    Google Scholar 

  32. Wolff FC (2014) Lift ticket prices and quality in French ski resorts: insights from a non-parametric analysis. Eur J Oper Res 237(3):1155–1164

    Article  Google Scholar 

Download references


We acknowledge the Ski resorts of Serbia and the Serbian mountaineer rescue service for providing data for this research.

Author information



Corresponding author

Correspondence to Sandro Radovanovic.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Radovanovic, S., Delibasic, B., Suknovic, M. et al. Where will the next ski injury occur? A system for visual and predictive analytics of ski injuries. Oper Res Int J 19, 973–992 (2019). https://doi.org/10.1007/s12351-018-00449-x

Download citation


  • Ski injury prediction
  • Data visualization
  • Lasso logistic regression