The current study aims to investigate the aberrant driving behaviour and risk involvement of Iranian taxi drivers. The sample comprised 405 Iranian taxi drivers, who were recruited with a cross-sectional design, using a self-completion questionnaire survey during October and November 2016. We contribute to the literature by understanding how and to what extent the socioeconomic, demographic, driving, and aberrant driving behaviours influence risk involvement (accident involvement and traffic tickets). The validated 27-item Driver Behaviour Questionnaire (DBQ) was applied to measure aberrant driving behaviour. The results from valid observations (n = 381) explored a four-factor solution (including errors, ordinary violations, lapses, and aggressive violations) of the DBQ. The results also showed that being a single driver, having a high annual driving mileage, and a high number of daily taxi trips were positively associated with accident involvement. Furthermore, there was a positive correlation between the more ordinary violations and aggressive violations and accident involvement. Establishing better training and qualification mechanisms for taxi drivers could be considered by traffic safety experts in order to reduce ordinary and aggressive violations.

Class imbalance presents a notable challenge in accurately classifying severe crash outcomes, which typically constitute the minority class. Ignoring class imbalance may lead to biased or misleading interpretations. Moreover, relying on traditional resampling techniques results in potential issues like overfitting, and information loss. Hence, this study proposes the Improved Balanced Random Forest (iBRF), a novel ensemble framework designed to combine various resampling techniques with ensemble learning to derive a model that addresses the challenge of class imbalance. The iBRF framework utilizes all minority cases and bootstrapped samples of the majority. SMOTE augments additional minority‑class instances, while the Neighborhood Cleaning Rule (NCR) and Random Undersampling (RUS) remove majority‑class instances to reduce noise and class overlap. The balanced data is utilized to train a decision tree in each iteration. Finally, a weighted soft voting based on the G-mean of each tree generates the final predictions. The performance of iBRF is tested using G-mean, and Matthews Correlation Coefficient (MCC) on holdout data (30%) and compared against other machine learning models designed for imbalanced datasets. iBRF achieves better performance than other resampling (SMOTE, RUS, NCR, and CTGANs) and state-of-the-art ensemble learning approaches (XGBoost, RF, LightGBM, RUSBoost, SMOTEBagging, SMOTEBoost, UnderBagging, OverBagging, and OverBoost) based on balanced metrics. The iBRF algorithm substantially improves the absolute G‑Mean of the simple RF and SMOTE‑RF models by 9.30 and 4.50 percentage points, respectively. The iBRF algorithm not only enhances classification performance but also helps identify risk factors associated with the minority class, which almost always correspond to severe‑outcome crashes and the focus of studies.