One of the important tasks that we have to face in a real world application is the task ofrnclassifying par1icular situation or events as belonging to a certain class. Risk assessment inrninsurance policies is one example that can be viewed as classification problem. In order tornsolve these kinds of problems we must build an accurate classifier system or model. Datarnmining techniques are powerful tools in addressing such problems.rnThis research describes the development of predictive model, which determines the riskrnexposure of motor insurance policies. Decision tree and neural network were used inrndeveloping the model. Since rejections of policy renewal are rare at Nyala Insurance SC.rn(NlSCO), where the research was conducted as a case study, policies were classified into onernof the three possible groups (Low, Medium, or High risk) on the basis of annual assessmentrnmade by NISCO. Six variables were extracted from the 25 variab les used in this study. 940rnfacts (90% of the working dataset) were used to build both decision tree and neural networkrnmodels. The remaining 116 (10 %) of the dataset were used to validate the performance of thernmodels. The decision tree model, selected based on the meaningfulness of the rules extractedrnfrom it, correctly classified 95.69% of the validation set, and the classification accuracy forrnlow, medium and high risk policies are 98. 15%, 94.12%, and 92.86% respectively. The neuralrnnetwork model correctly classified 92.24 % of the validation set, high-risk groups arerncorrectly classified, and low and medium-risk groups are classified with accuracy of 98 .1 5%rnand 76.47% respectively. Some possible explanations for the relatively low performance ofrnthe neural network with medium policies are given. In addition, an interesting pattern wasrnfound between the two models that some policies classifieds by decision tree were correctlyrnclassified by neural networks, and vice versa. This is a good indication that the hybrid of therntwo models may result in better performance.