For the classification of the best car is not something easy, because the choice of each
other has advantages and disadvantages of each. This paper discusses the decision to choose the
best car alternative. So far, the probability of choice is determined more by the intuition and
subjectivity of decision makers, who tend to be biased in view of human cognitive limitations. To solve
this problem the author uses the K Nearest Neighbor (KNN) method which is proven by the Weka tool,
and is applied using matlab. The results of this experiment are that the amount of data as much as 14
has an accuracy rate of 78.57% and an RMSE of 0.23, while the amount of data of 1728 has an
accuracy rate of 95.78%, an RMSE of 0.19 and ROC area 0.99. Shows the greater the amount of data
the higher the accuracy level.
PEER REVIEW
Larose (2005). Discovering Knowledge In Data
Central Connecticut State University.
United States of America
Brammer (2007). Principles of Data Mining.
Digital Professor of Information Technology,
University of Portsmouth, UK.
Witten.( 2011 ). Data Mining Practical Machine
Learning Tools and Techniques Library of
Congress Cataloging-in-Publication Data..
Cunningham and Jane Delany.(2007). k-
Nearest Neighbour Classifiers, Dublin
Institute of Technology.
Tedy Rismawan, Ardhitya Wiedha Irawan,
Wahyu Prabowo, Sri Kusumadewi.(2008).
sistem pendukung keputusan berbasis
pocket pc sebagai penentu status gizi
menggunakan metode knn (k-nearest
neighbor). Fakultas Teknologi Industri,
Universitas Islam Indonesia
Alexander Hinneburg et all. ( 2000 ). What is
the nearest neighbor in high dimensional
spaces?. Proceedings of the 26th VLDB
Conference, Cairo, Egypt
Astrid Darmawan (2012). pembuatan aplikasi
data mining untuk memprediksi masa studi
mahasiswa menggunakan algoritma knearest
neighborhood. fakultas teknik dan
ilmu computer universitas komputer
Indonesia.
Olga Kudoyan. (2010). The incremental
benefits of the nearest neighbor forecast of
u.s. energy commodity prices: Thesis
Texas A&M University