Background: Immunization is one of the most cost effective and efficient interventions savingrnthe lives of many millions of infants and children from dying of infectious and preventablerndiseases. In 2007, approximately 27 million infants are not vaccinated against commonrnchildhood diseases and 2â€“3 million children are dying annually from easily preventable diseasesrnand many more fall ill. rn Objective: The research has a general objective of construct a predictive model using datarnmining technology that helps to predict the infantsâ€™ immunization status in Ethiopia. The resultrnof the study is expected to be important for different parties such as infants, health professionals,rnpolicy makers, programmers and researchers. rnMethodology: This study is guided by a Hybrid-data mining model which is a six steprnknowledge discovery process model such as understanding of the problem, understanding of therndata, preparation of the data, data mining, and evaluation of the discovered knowledge and use ofrnthe discovered knowledge. The study has used 8,210 instances, 12 predicting and one outcomernvariables to run the experiments. Due to the nature of the problem and attributes contained in therndataset, classification data mining task is selected to build the classifier models. The miningrnalgorithms; J48 decision tree, sequence minimal optimization support vector machine, multilayer rnperceptron neural network and partial decision tree rule induction are used in all experiment duernto their popularity in recent related works. Ten-fold cross validation technique is used to trainrnand test the classifier models. Performance of the models is compared using accuracy, truernpositive rate, false positive rate, and the area under the Receiver Operating Characteristics curve. rnResult: The J48 decision tree has given the best classification and a better predictive accuracy ofrnthe infant immunization status in Ethiopia. The experiment has generated a model with accuracyrnof 62.5%, weighted precision of 62.5% and weighted ROC area of 67.6% for the J48 decisionrntree. And if place of delivery = home region = Affar AND mother-education-level = noeducationrnANDrnwealth-statusrn=rnpoorrnANDrnlistening-to-radiorn=rnnot-at-allrnANDrnmother-agern=rn2529rnrnAND parity = 6-7 then Unimmunised (10.0/1.0).Therefore, increase awareness creationrnamong women in pastoralist communities so as to enhance vaccine coverage. rnConclusion: The results achieved from this research indicate that data mining is useful inrnbringing relevant information from large and complex EDHS dataset, and we can thisrninformation for predicting infant immunization status and decision making. The most importantrnattributes that determine infant immunization status were place of delivery, region, mother'srneducational level, listening to radio, father education level, residence, mother age, wealth status,rnparity, distance to health facility and marital status.