ABSTRACTÂ SPP payment at Surakarta Al-Islam Vocational School often experiences delays, this will cause disruption of school operational activities because the school tuition payment fund is mostly for operational costs for the development of school facilities and infrastructure. Therefore it is necessary to follow up the parents of students who experience late payment of tuition that can be predicted by the K-Nearest Neighbor method. To predict late payment of SPP, the parameters Income, Education, Family Dependents, and Age are used in calculating the closest distance between training data and testing data. The purpose of this study is to determine the accuracy of the prediction results of late payment of SPP by the K-Nearest Neighbor method. The prediction results can be used by the school to provide a letter of payment of SPP payments to prospective guardians of students so that when the payment schedule has entered the payment schedule parents of guardians do not experience latency in paying.Keywords: Prediction , K-Nearest Neighbor, Accurate