A tree-based extended model to predict intention to speed for taxi drivers.

• This study aims to develop a rational model of the intention to risky behaviour based on behavioural characteristics, demographic information, and the amount of exposure and comparing aggregate and disaggregate models of input variables. • In this study, the self-reported data of Tehran taxi drivers was collected in the form of a questionnaire based on the theory of planned behaviour, and then the amount of intention to commit violations was predicted and modeled using stepwise regression and decision tree regression. • The variables were compared and refined in two stages of exploratory factor analysis and stepwise regression before being entered into the tree regression model. • The results obtained from different modelling cases showed that the presence or absence of the exposure variable did not have much effect on the models. The inclusion of attitude, subjective norm, perceived behavioural control and descriptive norm increased the explained variance of intention to violate. The need to predict and understand drivers' intention to violate emphasizes the importance of developing a model based on the motives behind the action. This study aims to develop a model to predict a taxi driveŕs intention to speed in an urban area using variables including psychological factors, demographic information, and exposure. Aggregate (factor-based) and disaggregate (item-based) models of input variables will also be compared. In this study, the self-reported data on Tehran taxi drivers was collected in the form of a scenario-based questionnaire which is inspired by the Theory of Planned Behaviour (TPB). The intention to commit violations was predicted and modelled using stepwise regression and decision tree regression models. The results, based on the stepwise regression model showed a higher value of fitting score for an item-based linear model (R2 = 0.695), but the final model using the tree-based regression presented a better fit for the factored model (R2 = 0.746) considering the cross-validated model with the lowest deviation criteria (RMSD = 0.26). Furthermore, in this model attitude made the greatest contribution to the prediction of intention. The results obtained from the two different modelling approaches showed that exposure and age did not have much effect on the models. A main advantage of the current study is that the variables were compared and refined in two stages of exploratory factor analysis and stepwise regression before being entered into the tree regression model. In addition, the results of the factor-based model were compared with the item-based model. [ABSTRACT FROM AUTHOR]