Sistem Rekomendasi Deposito Berjangka Menggunakan Metode Random Forest: Studi Kasus Pada Bank Marketing UCI
Article Sidebar
Read Counter : 9
Download : 5
Main Article Content
Abstract
Perkembangan teknologi dan perubahan perilaku konsumen di era digital telah mendorong industri perbankan untuk mengadopsi pendekatan yang lebih inovatif dalam menawarkan produk dan layanan mereka, terutama deposito berjangka. Penelitian ini bertujuan untuk mengembangkan sistem rekomendasi deposito berjangka menggunakan metode Random Forest, dengan studi kasus pada dataset Bank Marketing UCI. Sistem ini dirancang untuk memberikan rekomendasi yang akurat dan personal berdasarkan data historis, preferensi, dan karakteristik individu nasabah. Metode Random Forest digunakan karena kemampuannya dalam menangani data besar dan kompleks, serta mengurangi risiko pemodelan berlebihan. Dataset yang digunakan mencakup 45.211 instances dengan 17 atribut, termasuk informasi demografis nasabah dan riwayat interaksi dengan bank. Hasil penelitian menunjukkan bahwa model Random Forest yang dikembangkan mencapai akurasi 91.56%, dengan presisi 65.47%, recall 52.12%, dan F1-score 58.04%. Analisis variable importance measure mengidentifikasi 'duration', 'age', dan 'balance' sebagai faktor paling berpengaruh dalam keputusan nasabah untuk berlangganan deposito berjangka. Implementasi sistem ini diharapkan dapat meningkatkan efektivitas pemasaran produk deposito berjangka dan meningkatkan kepuasan nasabah.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
This work is licensed under Creative Commons Attribution-ShareAlike 4.0 International License.
References
P. C. P. R. Sergio Moro, "A data-driven approach to predict the success of bank telemarketing," Decision Support System, vol. 62, pp. 22-31, 2014.
Y. M. M. U. N. Peter Appiahene, "Predicting Bank Operational Efficiency Using Machine Learning Algorithm: Comparative Study of Decision Tree, Random Forest, and Neural Networks," Advances in Fuzzy Systems, vol. 2020, no. 1, 2020.
T. C. Jia-Lang Seng, "An analytic approach to select data mining for business decision," Expert Systems with Applications, vol. 37, no. 12, pp. 8042-8057, 2010.
X. C. Yongfeng Zhang, "Explainable Recommendation: : A Survey and New Perspectives," Foundations and Trends® in Information Retrieval, vol. 14, no. 1, pp. 1-101, 2020.
S. N. A.-S. Lesly Alejandra Gonzalez Camacho, "Social network data to alleviate cold-start in recommender system: A systematic review," Information Processing & Management, vol. 54, no. 4, pp. 529-544, 2018.
S. S. Mamta Kalra, "Machine Learning and Deep Learning Techniques for Recommendation Systems: A Comprehensive Review," Harbin Engineering University, vol. 45, no. 5, pp. 158-172, 2024.
S. S. K. M. Martin Leo, "Machine Learning in Banking Risk Management: A Literature Review," Risks, vol. 7, no. 1, pp. 1-22, 2019.
L. Breiman, "Random Forests," Machine Learning, vol. 45, pp. 5-32, 2001.
P. Y.-x. X. J.-b. Xu Yong, "The Improvement of Personalized Recommendation System Based on Sparse Data of Financial Products," World Journal of Research and Review, vol. 7, no. 2, pp. 19-25, 2018.
J. F. R. O. C. J. S. Leo Breiman, Classification and Regression Trees, New York: Taylor & Francis, 1984.
R. T. J. F. Trevor Hastie, Ruppert, David. "The elements of statistical learning: data mining, inference, and prediction, New York: Springer, 2017.
S. P. A. C. Yogo Aryo Jatmiko, "Analisis Perbandingan Kinerja CART Konvensional, Bagging dan Random Forest Pada Klasifikasi Objek: Hasil Dari Dua Simulasi," Media Statistika, vol. 12, no. 1, pp. 1-12, 2019.
M.-L. Z. Zhi-Hua Zhou, "A Review on Multi-Label Learning Algorithms," IEEE transactions on knowledge and data engineering, vol. 26, no. 8, pp. 1819-1837, 2014.
R. H. Z. S. W. Z. Shufang Song, "Variable Importance Measure System Based on Advanced Random Forest," Computer Modeling in Engineering & Sciences, vol. 128, no. 1, pp. 65-85, 2021.