Assessing and mitigating traffic crash risks using interpretable machine learning techniques

Adnan Yousaf, Jianping Wu, Deqing Huang, Muhammad Zahid, Muhammad Faisal Habib, Amjad Pervez, Muhammad Hussain · 2026

Read Assessing and mitigating traffic crash risks using interpretable machine learning techniques by Adnan Yousaf, Jianping Wu, Deqing Huang, Muhammad Zahid, Muhammad Faisal Habib, Amjad Pervez, Muhammad Hussain (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13507384.txt.

Description

What makes a driver crash is partly behavior, and behavior can be measured. Adnan Yousaf and six co-authors survey 623 drivers in Pakistan about aggressive, risky, and careless habits, plus their crash history over three years. They then train three machine learning models to predict crash involvement, using an explanation method that shows which factors drive each prediction.

Aggressive and risky driving, errors, and violations all raised crash risk, and prior motorcycle experience mattered too. The XGBoost model predicted best, at 86 percent accuracy, ahead of its two rivals. The authors argue for behavior-focused remedies: enforcement against aggression, better driver education, and transition training for riders moving to cars. The study appears in 2026.

Catalog record

CREATORAdnan Yousaf, Jianping Wu, Deqing Huang, Muhammad Zahid, Muhammad Faisal Habib, Amjad Pervez, Muhammad Hussain
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE56 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC13507384

Browse the full library · About the Tower of Babel