Modelling and Assessing
the Severity of Road Traffic Accidents in Zambia, Using Data Mining Techniques
Modelling and Assessing the Severity of Road Traffic Accidents in Zambia, Using Data Mining Techniques
-
Pethias Siame 1
-
Department of Literature and Languages, Kwame Nkrumah University, Zambia
The main aim of this study was to identify and investigate drivers, road, weather, and motor Vehicle-related factors that contribute
to the severity of road traffic accidents in Zambia. This research develops a road traffic accident prediction model and compares
the performance of Decision Tree (J48), Rule Induction (PART), Naive Bayes, and Random Forest algorithms to select the best
performing algorithm in the prediction of the road traffic accident severity. Raw data was collected from the Zambia Police Service
Headquarters Traffic Department to construct the data set required for analysis using WEKA software. The efficiency of the
algorithms used in this research was evaluated by comparing the classification accuracy, the Receiver Operating Characteristics
curve, and the results shown in the confusion matrix. The results reveal that the J48 algorithm performed better than the other
three algorithms. The rules produced by the PART algorithm show that year, province, tire condition, car braking condition, driver’s
age, driver’s license grade, time, and lighting condition are the most important features in the classification of a road traffic
accident severity.
