Data mining is emerging as an important too l in many areas of research and industry.rnCompanies and organizations are increasingly interested in applying data mining tools tornincrease the value added by their data collections systems. Nowhere is this potential morernimportant than in the healthcare industry. As medical records systems become morernstandardized and commonplace, data quantity increases with much of it goingrnanalyzed. Data mining can begin to leverage some of this data into tools that helprnhealth organizations to organize data and make decisions.rnData related to HIV ) AIDS are available in VCT centers. A major objective of this thesisrnis to evaluate the potential applicability of data mining techniques in VCT, with the aimrnof developing a model that could help make informed decisions. Using the datasetsrncollected from OSSA, which is supported by CDC, and CRISP-OM as a knowledgerndiscovery process model findings of the research are presented using graphs and tabularrnformatsrnFor the clustering task the K-means and EM algorithms were tested U Sing WEKA.rnCluster generated by EM were appropriate for the problem at hand in generating similarrngroup. According to the results of these experiments it was possible to see similar groupsrnfrom VCT clients. The gender, martial status, and HIV test result, and education hasrnshown patterns.rnFor the class unification task, dices ion tree (J48 and Random tree) and neural networkrn(ANN) classifier are evaluated .Although AITN shows better accuracy than decision treernclassifier, the decision tree (J48) is appropriate for the datasets at hand and is used to buildrnthe classification model. Finally, cluster-derived class unification models are tested for theirrncross-validation accuracy and compared with non cluster generated classification ion model.rnThe outcomes of this research will serve users in the domain area, decision makers andrnplanners of HIV intervention program like CDC and MOH.