Family welfare is a family formed in legitimate marriage, spiritual needs and material worthy, devoted to God YME, have a harmonious relationship, harmonious and balanced with society and the environment. The government has implemented various family development programs prosperous. To support this, every year the government implements the family data collection process. Family data collection is considered an important step because it has many functions, primarily to understand the target group and to determine solutions to solve the problems of each target group. The search or discovery process of information and knowledge contained in the number of data can be done with data mining technology. Data mining is a term used to describe the discovery of knowledge in a database. In this case data mining can be used to determine the status of the prosperous family stage. The K-Nearest Neighbor (KNN) method, the Naive Bayes method and the Principal Component Analysis (PCA) are used for the proper classification of status stages. Based on the test results, the performance test of classification algorithm for case of determining status of prosperous family of Sidareja District for Naïve Bayes method using confusion matrix obtained 98.12% accuracy after added PCA feature selection to 97.73% while KNN method obtained accuracy of 98.86%, then after added PCA feature selection increased to 98.96%.