Open AccessSample Identification Approach by K-Means Clustering In Thinner Retail Market Segmentation
Author(s) -
Langgeng Listiyoko,
Marhaendro Purno
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1477/2/022004
Subject(s) - cluster analysis , sample (material) , market segmentation , identification (biology) , segmentation , cluster (spacecraft) , product (mathematics) , data set , computer science , set (abstract data type) , data mining , value (mathematics) , k means clustering , pattern recognition (psychology) , artificial intelligence , mathematics , machine learning , marketing , business , chemistry , botany , geometry , chromatography , biology , programming language
Ingredients identification of thinner sample in retail market is very easy to do by a special machine, and then the product would be copied. Then the problem is how to set the sample of competitor product into the segmentation based on many consideration aspects. Data mining helps user to identify whether the sample is a member of one segmentation or not based on the closest characteristic value that observed. K-means clustering calculate a numeric value of each sample product’s characteristic then classify into a number desired cluster. Data history has 21 existing products and classified into 4 cluster at the beginning, then two data tests (competitor products) put into the data set to identify what is the nearest cluster. The result of K-means clustering shows the first competitor as cluster_1 while the second one is cluster_3.