Fuzzy c-Means Clustering untuk Pengenalan Pola Studi kasus Data Saham

Abstract

Fuzzy Clustering is one of the five roles used by data mining experts to transform large amounts of data into useful information, and one method that is often and widely used is Fuzzy c-Means (FCM) Clustering. FCM is a data clustering technique where the existence of each data point in the cluster is based on the degree of membership. This study aims to see the pattern of data samples or data categories using FCM clustering. The analyzed data is stock data on Jakarta Stock Exchange (BEJ) in the Property and Real Estate sector (issuer group). The data mining processes comply Cross Industry Standard Process Model for Data mining Process (Crisp-DM), with several stages, starting with the stage of getting to know the business process (Business Understanding) then studying the data (Data Understanding), continuing with the Data Preparation stage, Modeling stage, Evaluation stage and finally the Deployment stage. In the modeling stage, the FCM model is used. FCM clustering model data mining can analyze data in large databases with many variables and complicated, especially to get patterns from the data. Then a Fuzzy Inference System (FIS) was built based on a known pattern for simulating input data into output data based on fuzzy logic.

Keywords: Fuzzy c-Means Clustering, Pattern Recognition