Data Mining untuk Nasabah Bank Telemarketing Menggunakan kombinasi Algoritm Naïve Bayes Dan Algoritma Genetik

Ahmad Ashifuddin Aqham, Kristoko Dwi Hartomo

Abstract

The strategy used for telemarketing by conducting promotional media, this strategy is a marketing method used by banks, in offering products to customers, banks, one of the products that will be offered is time deposits, the bank has difficulty in knowing the obstacles experienced by customers in making a decision to make deposits against the bank, so that later it will have the effect of a financial crisis at the bank. Telemarketing banks must have targets for customers, where customers have the potential to join one of the bank's products, namely deposits by looking at existing customer data.With the existing problems will be overcome by the datamining technique that will be used for this research is the Naïve Bayes algorithm and genetic algorithm which aims to predict the Telemarketing customers' sources sourced from public UCI Repsitory data so that the bank offers a product to the customer right at the target. Naïve Bayes test with experimental results of 86.71% accuracy while cross validation testing using Genetic algorithm produces high accuracy 90.27%, Root proves the prediction of time series data Naïve Bayes method and Genetics produces an accuracy of 90.27%, so it can be concluded that using the Naive Bayes algorithm and Genetics can optimize in predicting Telemarketing client decisions right in the deposit offer.

Keywords

telemarketing, naïve bayes, algoritma genetika

Full Text:

PDF

References

C. Ou, C. Liu, J. Huang and N. Zhong, "On Data Mining for Direct Marketing," Springer-Verlag Berlin, p. PP. 491–498., 2003.

D. T. LAROSE, Data Mining Methods and Models, ISBN-13 978-0-471-66656-1, America: Department of Mathematical Sciences Central Connecticut State University, 2006.

D. C. P. Buani, "Optimasi Algoritma Naïve Bayes dengan Menggunakan Algoritma Genetika untuk Prediksi Kesuburan (Fertility)," Evolusi, vol. 4, no. 1, pp. 54 - 63, 2016.

R. Wati, "Penerapan Algoritma Genetika Untuk Seleksi Fitur Pada Analisis Sentimen Review Jasa Maskapai Penerbangan Menggunakan Naive Bayes," Evolusi, vol. 4, no. 1, pp. 25 - 31, 2016.

O. Sumantri and M. Kambali, "Feature Selection Klasifikasi Kategori Cerita Pendek Menggunakan Naïve Bayes dan Algoritme Genetika," JNTETI, vol. 6, no. 3, pp. 301 - 3016, 2017.

Y. Wu, S. Huang, H. Ji, C. Zheng and C. Bai, "A Novel Bayes Defect Predictor Based on Information Diffusion Function," Knowledge-Based Systems, vol. 144, pp. 9-15, 2017.

S. A. Mostafa, A. Mustapha and M. a. Muhammad, "Examining multiple feature evaluation and classification methods," Cognitive Systems Research, vol. 54, pp. 90-99, 2019.

H. Muhammad, C. A. Prasojo, N. A. Sugianto, L. Surtiningsih and I. Cholissodin, "Optimasi Naïve Bayes Classifier Dengan Menggunakan Particle Swarm Optimization Pada Data Iris," Jurnal Teknologi Informasi dan Ilmu Komputer (JTIIK), vol. 4, no. 3, pp. 180-184, 2017.

A. D. Herlambang and S. H. Wijoyo, "Algoritma Naïve Bayes Untuk Klasifikasi Sumber Belajar Berbasis Teks Pada Mata Pelajaran Produktif Di Smk Rumpun Teknologi Informasi Dan Komunikasi," Jurnal Teknologi Informasi dan Ilmu Komputer (JTIIK) , vol. 6, no. 4, pp. 431-436 , 2019.

B. "Penerapan Algoritma Naïve Bayes Untuk Mengklasifikasi Data Nasabah Asuransi," TECHSI : Jurnal PenelitianTeknik Informatika, vol. 3, no. 2, pp. 127 - 146, 2013.

J. C. M. J. C. N. A. Zaidi, "Alleviating Naive Bayes Attribute Independence Assumption byAttributeWeighting," Journal of Machine Learning Research, vol. 1, no. 14, pp. 1947 - 1988, 2013.

S. Kusuma dewi, Artificial Intelligent., Yogyakarta: Graha Ilmu, 2003.

Z. Zukhri, Algoritma Genetika Metode Komputasi untuk Menyelesaikan Maslah Optimasi., Yogyakarta: Andi Offset, 20014.

A. M. D. Anita, Konsep Kecerdasan Buatan, Yogyakarta: Andi Offset., 2006.

V. d. F. Trevino, "GALGO: an R package for multivariate variable selection using genetic algorithms," Bioinformatics, vol. 22, p. 1154–1156., 2006.

Refbacks

  • There are currently no refbacks.