Road Traffic Accidents Severity Modelling in Malawi

One of the significant problems Malawi faces today is the rate at which road traffic accidents and deaths are happening on the roads of Malawi. It is very crucial to effectively address such a problem with a limited budget considering that Malawi is a developing country. To supplement the current safety measures, traffic accidents data mining using machine learning models was considered. Being able to predict the severity of an accident as well as determining the weight each attribute contributes to the severity could help authorities make informed decisions. Therefore, this research aimed at modeling the severity of road accidents in Malawi to help reduce traffic accidents or the severity with limited budgetary resources. Using python, three classification algorithms were employed to model the severity of an accident. The algorithms included; Decision trees, Logistic regression and Support Vector Machines. These models were evaluated using accuracy, precision, recall, and F1-score. The logistic regression performed better than the other two and after fitting the model it was discovered that the top three attributes that contributed to fatal accidents were accidents involving a moving vehicle and a pedestrian, accidents that occurred at Dawn or Dust, and accidents involving a moving vehicle and a bicycle