Determining Eligible Villages for Mobile Services using K-NN Algorithm

To maximize and get population document services closer to the community, Disdukcapil district of Alor provides mobile by visiting people in remote villages which difficult-to-reach service centres city. Due a large number limited time costs, not all can be served, so kNN algorithm is needed determine are eligible served. The criteria used this determination village distance, difficulty level, ownership (Birth Certificate, KIA, family card, KTPel). classes that will determined "Very eligible", "Eligible", "Not eligible". By applying Z-Score normalization with value K=5, classification gets 94.12% accuracy, while non-normalized only 88.24% accuracy. Thus, training data improve algorithm's accuracy determining for "ball pick-up" or services.