Klasifikasi User yang Berpotensi Melakukan Pembelian Barang Online Menggunakan Algoritme Weighted K-Nearest Neighbor


  • Valentina Yohana Senduk Universitas Sanata Dharma
  • Eko Hari Parmadi Universitas Sanata Dharma


e-commerce, web clickstream, weighted k-nearest neighbor, classification


Electronic commerce is an exchange using technology as an intermediary between various parties (individuals or organizations) as well as electronic-based intra or interorganizational exchange activities. The most commonly used interface is the web browser. Visitor’s behavior on a web site can be analyzed using a classification algorithm on the data order of site visits or commonly known as web clickstream. In this study the weighted k-nearest neighbor algorithm is used to classify users who have the potential to make online based purchase on public data on a web clickstream data of an e-commerce. The weighted k-nearest neighbor method makes the classification based on the label that has the highest number of distance weights at the nearest k-neighbor from the classified data. The output of this system is the classification of users who have the potential to purchase goods online and those who do not. Researchers conducted an attribute selection experiment with variations in k and variations in the number of attributes based on the results of rank information gain and obtained the 2 most influential attributes in the classification namely Page Values and Exit Rates. Testing to find the most optimal k was done on 7,632 data using 3-fold cross validation and produced the highest accuracy of 86.2028% at k = 65.


Bicego, M. & Loog, M.. (2016). Weighted K-Nearest Neighbor revisited. 1642-1647. 10.1109/ICPR.2016.7899872.

Gorunescu, Florin. (2011). Data Mining : Concepts, Model, and Techniques. Springer.

Han, Jiawei, dkk. (2012). Data Mining : Concepts and Techniques, Elsevier Inc.

Kusrini dan Luthfi, E.T.(2009). Algoritma Data Mining. Yogyakarta: ANDI.

Prasetyo, E. (2014). Data Mining – Mengolah Data Menjadi Informasi Menggunakan Matlab. Penerbit Andi : Yogyakarta.

Schliep, K. P. (2004). Weighted k-nearest-neighbor techniques and ordinal classification. Open Access LMU. https://doi.org/10.5282/ubm/epub.1769




How to Cite

Senduk, V. Y. ., & Parmadi, E. H. (2022). Klasifikasi User yang Berpotensi Melakukan Pembelian Barang Online Menggunakan Algoritme Weighted K-Nearest Neighbor . Prosiding Seminar Nasional Ilmu Sosial Dan Teknologi (SNISTEK), 4, 109–114. Retrieved from https://ejournal.upbatam.ac.id/index.php/prosiding/article/view/5224