Metode Pembobotan Jarak dengan Koefisien Variasi untuk Mengatasi Kelemahan Euclidean Distance pada Algoritma k-Nearest Neighbor

k-Nearest Neighbor (k-NN) is one of the classification algorithms which becomes top 10 in data mining. k-NN simple and easy to apply. However, results are greatly influenced by scale input. All its attributes considered equally important Euclidean distance, but inappropriate with relevance each attribute. Thus, it makes decreased. Some more or less or, fact, irrelevant determining results. To overcome disadvantage k-NN, Zolghadri, Parvinnia, John proposed Weighted Distance Nearest (WDNN) having performance better than k-NN. when result k >1, decrease. Gou Dual Voting (DWKNN) DWKNN focused label weighted voting. It applied distance without attribute weighting. This might cause all attribute, make research Coefficient Variation Weighting (CVWKNN) integrating MinMax normalization distance. Seven public datasets from UCI Machine Learning Repository were used this research. The Friedman test Nemenyi post hoc for accuracy showed CVWKNN had significantly different compared algorithm.