SELEKSI ATRIBUT PADA ALGORITMA C4.5 MENGGUNAKAN GENETIK ALGORITMA DAN BAGGING UNTUK ANALISA KELAYAKAN PEMBERIAN KREDIT
Abstract
According to the banking ACT No. 9 of 1992 is the provision of credit or money bills which can dipersama-kan with it, based on the approval of an agreement between the bank pinjam-meminjam with other parties that require that the borrower to pay off a loan after a certain period of time with the giving of flowers. Credit analysis aims to evaluate the customer able to or not in fulfilling obligations. In analyzing the sometimes an analyst is not accurate in analyzing causing bad credit. Of the problems that existed then used a method of classification for an analysis of the feasibility of granting credit using a model algorithm Genetic Algorithm with C4.5 (AG) as a selection of attributes and bagging method to improve accuracy. After testing two models namely algorithm C4.5 and C4.5 with Genetic Algorithms (AG) and the results obtained bagging method is the algorithm C 4.5 produces a value accuracy 93,47% and AUC values 0,932 with excellent levels of Clasification diagnose but after Genetic Algorithm added (AG) and increased accuracy value bagging 2.87% to 96,34% and AUC values increased 0.044 became 0.976.
Keywords: Credit, the algorithm C 4.5, Genetic Algorithms (GA), Bagging
Menurut UU Perbankan No.9 Tahun 1992 kredit merupakan penyediaan uang atau tagihan yang dapat dipersama-kan dengan itu, berdasarkan persetujuan atau kesepakatan pinjam-meminjam antara bank dengan pihak lain yang mewajibkan pihak peminjam untuk melunasi utangnya setelah jangka waktu tertentu dengan pemberian bunga. Analisa kredit bertujuan untuk mengevaluasi nasabah mampu atau tidak dalam memenuhi kewajiban. Dalam menganalisa terkadang seorang analis tidak akurat dalam menganalisa sehingga menyebabkan kredit macet. Dari permasalahan yang ada maka digunakan sebuah metode klasifikasi untuk analisis kelayakan pemberian kredit menggunakan model algoritma C4.5 dengan Algoritma Genetika (AG) sebagai seleksi atribut dan metode bagging untuk meningkatkan akurasi. Setelah dilakukan pengujian dua model yaitu algoritma C4.5 dan C4.5 dengan Algoritma Genetika (AG) dan metode bagging hasil yang diperoleh adalah algoritma C4.5 menghasilkan nilai akurasi 93,47 % dan nilai AUC 0,932 dengan tingkat diagnose excellent Clasification namun setelah ditambahkan Algoritma Genetika(AG) dan bagging nilai akurasi meningkat 2,87% menjadi 96,34 % dan nilai AUC meningkat 0.044 menjadi 0.976.
Kata kunci: Kredit, Algoritma C4.5, Algoritma Genetika (AG), Bagging
Full Text:
PDFReferences
R. Indonesia, UU Perbankan No. 9 1992. 1995, pp. 1–20.
O. Akbilgic and H. Bozdogan, “A new supervised classification of credit approval data via the hybridized RBF neural network model using information complexity,” in Studies in Classification, Data Analysis, and Knowledge Organization, vol. 48, 2015, pp. 13–27.
S. Oreski and G. Oreski, “Genetic algorithm-based heuristic for feature selection in credit risk assessment,” Expert Syst. Appl., vol. 41, no. 4 PART 2, pp. 2052–2064, 2014.
J. Zurada, “Could decision trees improve the classification accuracy and interpretability of loan granting decisions?,” in Proceedings of the Annual Hawaii International Conference on System Sciences, 2010.
A. S. U. Refailzadeh Payam, Lei Tang, Huan Liu, “Cross-Validation.”
J. L. Zhang and W. K. Härdle, “The Bayesian Additive Classification Tree applied to credit risk modelling,” Comput. Stat. Data Anal., vol. 54, no. 5, pp. 1197–1205, 2010.
L. Yu, G. Chen, A. Koronios, S. Zhu, and X. Guo, “Application and Comparison of Classification Techniques in Controlling Credit Risk,” World, pp. 2007–2007.
C. Jun, Y. Cho, and H. Lee, “Improving Tree-based Classification Rules Using a Particle Swarm Optimization,” 2017.
J. Abellán and A. R. Masegosa, “Bagging schemes on the presence of class noise in classification,” Expert Syst. Appl., vol. 39, no. 8, pp. 6827–6837, 2012.
B. K. Sarkar, S. S. Sana, and K. Chaudhuri, “Selecting informative rules with parallel genetic algorithm in classification problem,” Appl. Math. Comput., vol. 218, no. 7, 2011.
C. W. Dawson, “Project in computing and information system,” 2009.
T. D. Larose, “Discovering Knowledge in Data an Introduction to Data Mining,” 2005.
DOI: http://dx.doi.org/10.20527/klik.v4i2.99
Copyright (c) 2017 KLIK - KUMPULAN JURNAL ILMU KOMPUTER
This work is licensed under a Creative Commons Attribution 4.0 International License.
This work is licensed under a Creative Commons Attribution 4.0 International License. View My Stats