One of the important tasks that we face in real world application is the task ofrnclassifying particular situation or events as belonging to a certain class. Riskrnassessment in insurance policies is one of the many areas, which uses classification asrnproblem solving approach.In order to solve problems whose solution could be categorical, we must buildrnclassification models. Data mining techniques have powerful tools for building modelsrnthereby addressing the problems This research study addresses the issues, techniques, and feasibility of building andrndeploying predictive model (s), which determines the risk exposure of individuals, i.e.rnthe study was based on claims data of Personal accident at Ethiopian InsurancernCorporation.Ethiopian Insurance Corporation classifies claims into two classes as Small claim andrnBig claim. To meet the objectives of the research, I,600-dataset records, each recordsrnhaving 23 attributes had been collected. But after the data is p reprocessed, the totalrndatasets records used for this study were reduced to 1543. And among the 23 attributes,rn6 of them were selected by discussing with the insurance experts for final modelrnbuilding.A close examination about the distribution of the data reveals that the data has anrnimbalanced distribution, which affects the accuracy of the model in favor of therndominant class, in this case the "Small" class. Thus, in order to solve this problem,rndataset balancing based on "PAcc_ Within" was taken and the result has shown that thernaccuracy was improved by far. Beside this, the researcher has found that the frequency occurrence (class distribution)rnof the values of an attribute has a great impact on the accuracy of the model.rnLastly, analyzing the economic impact of the models and a separate accuracy measuresrnfor each class of risk category is used in order to compare the models and select one forrndeployment. Accordingly a model, which was built using knowledge SEEKERrnalgorithm and balanced data partitioning, based on "PAcc_ Within" attribute wasrnselected as a final model. This model has an overall accuracy of 96.61 % and arnclassification error of 0.29% and 27% for Small and Big risk claim classes respectively