METODE FUZZY CHAID (CHI-SQUARED AUTOMATIC INTERACTION DETECTION) PADA SEGMENTASI PASAR: STUDI KASUS : ANALISIS KREDIT MACET DI BMT EL BUMMI 372 YOGYAKARTA

• Main Authors: , Muhammad Muhajir, , Dr. Abdurakhman, M.Si.
• Format: Theses and Dissertations NonPeerReviewed
• Published: [Yogyakarta] : Universitas Gadjah Mada 2014
• Subjects: ETD
• Online Access: https://repository.ugm.ac.id/133389/; http://etd.ugm.ac.id/index.php?mod=penelitian_detail&sub=PenelitianDetail&act=view&typ=html&buku_id=74038

Analyzing market segmentation can be done by classification based on relationship credit status. One of the conventional method that common to be used is CHAID (Chi squared Automatic Interaction Detection), which is a conventional method using crisp data. In this research, it is used a linguistic term as an input data because the credit status rating can be expressed using the language (linguistic term) and it is a set of data in fuzzy form. To generate the input data in the form of fuzzy it is performed a fuzzification process on the data after construction of decision tree using CHAID analysis. The process is called Fuzzy CHAID. Fuzzy CHAID method can handle classification problems uncertainty in data, which interrelated with human thinking and human perception. The induction fuzzy algorithm to CHAID can be used to soften the sharp decision boundaries on the traditional CHAID algorithm. Keywords: Relationship Segmentation, Classification, CHAID, Fuzzy CHAID