Anemia is recognized as major public health problems globally with diverse consequences for human health as well as socioeconomic development (WHO, 2015). Globally, more than two-fifths of young children in the world are affected by anemia. In Ethiopia, based on the 2005, 2011, and 2016 EDHS, 54%, 44% and 57 of children aged 6 to 59 months are anemic, respectively. The aim of this study is to develop a model for predict the status of anemia among children aged 6 to 59 months using data mining techniques. This study followed hybrid methodology of Knowledge Discovery Process to achieve the goal of building a predictive model using data mining techniques and used secondary data from the 2016 Ethiopia Demographic and Health Survey (EDHS) dataset of 8603 records of both anemic and not anemic children aged 6 to 59 months through five experiments and ten scenarios. WEKA 3.9.3 data mining tools and classification techniques such as J48 decision tree, Naïve Bayes and PART rule induction algorithms were employed as means to address the research problem. Model comparison is done based on TP (sensitivity) and FP (specificity) rates, precision, recall, F-measure, ROC area and accuracy. 10-fold cross validation test option is used to check the performances of each classifier. In this particular study, the predictive model developed using J48 pruned with all attributes perform better in predicting anemic cases with an accuracy of 91.805%. Generally the results from this study were encouraging and confirmed that applying data mining techniques could indeed support a predictive model building task that predicts anemic status children aged 6 to 59 months in Ethiopia. Thus, the outcome of this study helps health care planners and policy makers to design a proper and suitable preventive and control program to combat anemia. In the future, integrating large demographic and health survey dataset and clinical dataset, employing other classification algorithms, tools and techniques could yield better results.