PREDICTING THE LOAN RISK TOWARDS NEW CUSTOMER APPLYING DATA MINING USING NEAREST NEIGHBOR ALGORITHM
Samsir (a*), Suparno (b), M. Giatman (c)
a,b,c) Department of Engineering, Technology and Vocational Education
Padang State University
Jl. Prof. Dr. Hamka Air Tawar Padang, West Sumatra, Indonesia
Email : samsirst111[at]gmail.com
Abstract
Unstable economic conditions require Bank must be careful in deciding towards lending customers. Banks should not take the risk of giving loans to customers who cannot afford to pay. This study aims to assist bank in predicting lending. The study was conducted at the Bank Perkreditan Rakyat in medan. The study was conducted applying data mining using the nearest neighbor algorithm. This algorithm was chosen because the nearest neighbor can calculate the closeness between new cases and old cases based on matching weights from a number of existing features. This algorithm will calculate the closeness with predetermined criteria. Hoped bank will be helped in making predictions.
Keywords: data mining, nearest neighbor, loan risk
Topic: Computer and Communication Engineering