International Journal of Civil Engineering

, Volume 15, Issue 4, pp 653–662 | Cite as

Identifying the Most Important Factors in the At-Fault Probability of Motorcyclists by Data Mining, Based on Classification Tree Models

  • Mohammad Bagher Anvari
  • Ali Tavakoli KashaniEmail author
  • Rahim Rabieyan
Research Paper


The motorcycle is considered one of the most applicable transportation modes for various trips in Iran. According to a 2011 report by Iran’s Police Department, motorcyclists and their passengers accounted for almost 25% of all crash fatalities. The objective of this study is to identify the most important factors that contribute to the fault of motorcyclists involved in crashes. The classification and regression trees model is used in this research to differentiate between at-fault and not-at-fault cases. The results show collision type to be the most determining factor for at-fault probability of motorcyclists. According to this fact, the probability of rear-end collision is the highest, while the probability of side collisions is the lowest. Other factors involved vary according to the collision type. Factors affecting rear-end collisions the most are passenger characteristics and the rider’s age. However, side collisions are mainly due to lighting conditions and area types (urban and rural roads). Finally, this paper suggests that training riders and installing warning systems that warn drivers when they are too close to motorcycles can reduce rear-end and side collisions to a great extent.


Motorcycle Being at-fault Classification and regression trees Passengers 


  1. 1.
    Vlahogianni EI, Yannis G, Golias JC (2012) Overview of critical risk factors in Power-Two-Wheeler safety. Accid Anal Prev 49:12–22CrossRefGoogle Scholar
  2. 2.
    Haque MM, Chin HC, Huang H (2009) Modeling fault among motorcyclists involved in crashes. Accid Anal Prev 41(2):327–335CrossRefGoogle Scholar
  3. 3.
    Lardelli-Claret P et al (2005) Driver dependent factors and the risk of causing a collision for two wheeled motor vehicles. Inj Prev 11(4):225–231CrossRefGoogle Scholar
  4. 4.
    Chang HL, Yeh TH (2007) Motorcyclist accident involvement by age, gender, and risky behaviors in Taipei, Taiwan. Transp Res Part F Traffic Psychol Behav 10(2):109–122MathSciNetCrossRefGoogle Scholar
  5. 5.
    Perez-Fuster P et al (2013) Modeling offenses among motorcyclists involved in crashes in Spain. Accid Anal Prev 56(0):95–102CrossRefGoogle Scholar
  6. 6.
    Liu CC, Hosking SG, Lenné MG (2009) Hazard perception abilities of experienced and novice motorcyclists: an interactive simulator experiment. Transp Res Part F Traffic Psychol Behav 12(4):325–334CrossRefGoogle Scholar
  7. 7.
    Rutter DR, Quine L (1996) Age and experience in motorcycling safety. Accid Anal Prev 28(1):15–21CrossRefGoogle Scholar
  8. 8.
    Moskal A, Martin JL, Laumon B (2012) Risk factors for injury accidents among moped and motorcycle riders. Accid Anal Prev 49:5–11CrossRefGoogle Scholar
  9. 9.
    Baldi S, Baer JD, Cook AL (2005) Identifying best practices states in motorcycle rider education and licensing. J Saf Res 36(1):19–32CrossRefGoogle Scholar
  10. 10.
    Schneider Iv WH et al (2012) Examination of factors determining fault in two-vehicle motorcycle crashes. Accid Anal Prev 45:669–676CrossRefGoogle Scholar
  11. 11.
    Wanvik PO (2009) Effects of road lighting: an analysis based on Dutch accident statistics 1987–2006. Accid Anal Prev 41(1):123–128CrossRefGoogle Scholar
  12. 12.
    Haque MM, Chin HC, Debnath AK (2012) An investigation on multi-vehicle motorcycle crashes using log-linear models. Saf Sci 50(2):352–362CrossRefGoogle Scholar
  13. 13.
    Schneider WH, Savolainen PT, Moore DN (2010) Effects of horizontal curvature on single-vehicle motorcycle crashes along rural two-lane highways. Transp Res Rec 2194(1):91–98CrossRefGoogle Scholar
  14. 14.
    Bosurgi G, Bongiorno N, Pellegrino O (2016) A nonlinear model to predict drivers’ track paths along a curve. Int J Civil Eng 14(5):1–10CrossRefGoogle Scholar
  15. 15.
    Luque R, Castro M (2016) Highway Geometric design consistency: speed models and local or global assessment. Int J Civil Eng 14(6):1–9CrossRefGoogle Scholar
  16. 16.
    Kashani AT, Rabieyan R, Besharati MM (2014) A data mining approach to investigate the factors influencing the crash severity of motorcycle pillion passengers. J Saf Res 51:93–98CrossRefGoogle Scholar
  17. 17.
    Breiman L (1998) Classification and regression trees. Chapman & Hall, Boca RatonGoogle Scholar
  18. 18.
    de Oña J, López G, Abellán J (2013) Extracting decision rules from police accident reports through decision trees. Accid Anal Prev 50(0):1151–1160CrossRefGoogle Scholar
  19. 19.
    Pande A, Abdel-Aty M (2009) Market basket analysis of crash data from large jurisdictions and its potential as a decision support tool. Saf Sci 47(1):145–154CrossRefGoogle Scholar
  20. 20.
    Montella A et al (2012) Analysis of powered two-wheeler crashes in Italy by classification trees and rules discovery. Accid Anal Prev 49:58–72CrossRefGoogle Scholar
  21. 21.
    Jiang X (2005) An investigation of the underlying assumptions of quasi-induced exposure. Michigan State University. Department of Civil and Environmental EngineeringGoogle Scholar
  22. 22.
    Kashani AT, Mohaymany AS (2011) Analysis of the traffic injury severity on two-lane, two-way rural roads based on classification tree models. Saf Sci 49(10):1314–1320CrossRefGoogle Scholar
  23. 23.
    Hing, JYC, Stamatiadis NL (2003) Aultman-Hall, Evaluating the impact of passengers on the safety of older drivers. J Saf Res 34(4):343–351CrossRefGoogle Scholar
  24. 24.
    Engström I et al (2008) Young drivers—Reduced crash risk with passengers in the vehicle. Accid Anal Prev 40(1):341–348MathSciNetCrossRefGoogle Scholar
  25. 25.
    Braitman KA, Chaudhary NK, McCartt AT (2011) Effect of passenger presence on older drivers’ risk of fatal crash involvement, I.I.H. Safety (ed) p 16Google Scholar
  26. 26.
    Li M-D et al (2009) Survival hazards of road environment factors between motor-vehicles and motorcycles. Accid Anal Prev 41(5):938–947CrossRefGoogle Scholar

Copyright information

© Iran University of Science and Technology 2017

Authors and Affiliations

  • Mohammad Bagher Anvari
    • 1
  • Ali Tavakoli Kashani
    • 1
    Email author
  • Rahim Rabieyan
    • 1
  1. 1.School of Civil EngineeringIran University of Science and TechnologyTehranIran

Personalised recommendations