Sistem Rekomendasi Pembelian Produk Kesehatan pada E-Commerce ABC berbasis Graph Database Amazon Neptune menggunakan Metode Hybrid Content-Collaborative Filtering
DOI:
https://doi.org/10.24002/jbi.v12i2.4623Abstract
Abstract. Recommendation System of Health Product Purchasing at ABC E-Commerce System based on Amazon Neptune’s Graph Database using Hybrid ContentCollaborative Filtering Method.Health products purchased by society, either in drugstores or pharmacies may vary according to their needs. ABC e-commerce is a Business to Business (B2B)-based e-commerce owned by PT XYZ. As a health product sales system from distributors to drug stores/pharmacies, they still do not have a health product purchase recommendation system yet. The recommendation system is needed to provide recommendations of health products for the customers. Amazon Neptune is implemented in this research to build a health product recommendation system. The hybrid contentcollaborative filtering method is used to generate complete recommendations based on content attributes and user habits. The datasets were product data, product categories, customers, product principals, and data of products trading. This research produces a health products recommendations model at ABC e-commerce with android based using web services. The implementation can provide recommendations of health products that can be accessed in real-time by customers.
Keywords: health products, recommendation systems, graph database, Amazon Neptune, hybrid content-collaborative filtering
Abstrak. Produk kesehatan yang dibeli masyarakat, melalui toko obat/apotek, dapat berbeda sesuai kebutuhan. E-commerce ABC berbasis Business to Business (B2B) milik PT XYZ sebagai sistem penjualan produk kesehatan dari distributor kepada toko obat/apotek belum memiliki sistem rekomendasi pembelian produk kesehatan. Sistem rekomendasi sebagai pengembangan fitur e-commerce ABC diperlukan untuk memberikan rekomendasi produk kesehatan yang sesuai dengan keadaan setiap pelanggan. Amazon Neptune sebagai graph database service yang dapat mengelola relasi dalam data yang saling terhubung, digunakan dalam penelitian untuk membangun sistem rekomendasi produk kesehatan. Metode hybrid content-collaborative filtering digunakan untuk menghasilkan rekomendasi yang lengkap berdasarkan atribut konten dan kebiasaan pengguna. Dataset yang digunakan meliputi data produk, kategori produk, pelanggan, principal, serta data jual-beli produk di e-commerce ABC. Penelitian ini menghasilkan model rekomendasi produk kesehatan yang diimplementasikan pada e-commerce ABC berbasis Android menggunakan web service. Implementasi tersebut memberikan rekomendasi produk kesehatan yang dapat diakses secara real-time oleh pelanggan pada saat menggunakan ecommerce ABC.
Kata Kunci: produk kesehatan, sistem rekomendasi, graph database, Amazon Neptune, hybrid content-collaborative filtering
References
Herdi, Hafizh. (2013). Sekilas Tentang Sistem Rekomendasi (Recommender System). TWOH&Co. [Daring]. Tersedia: https://www.twoh.co/2013/05/17/sekilas-tentang-sistem-rekomendasi-recommender-system/2/
Rizky A, Rangga. (Sep 28, 2018). Bagaimana Sistem Rekomendasi Berkerja?. Medium. [Daring]. Tersedia: https://medium.com/@ranggaantok/bagaimana-sistem-rekomendasi-berkerja-e749dac64816
Robinson, I., Webber, J., & Eifrem. E., (2015). Graph Databases 2nd Edition Compliments of neo4j, 2nd ed. United States of America: O’Reilly Media, Inc., 1005 Gravenstein Highway North, Sebastopol, CA 95472.
Anonim. Amazon Neptune - Fast, Reliable Graph Database built for the cloud. Amazon. [Daring]. Tersedia: https://aws.amazon.com/neptune/
Yuhanna, N., Leganza, G., & Weber, D. (2020). The Forrester WaveTM Graph Data Platforms, Q4 2020. Forrester. [Daring]. Tersedia: https://www.forrester.com/report/The+Forrester+Wave+Graph+Data+Platforms+Q4+2020/-/E-RES161455#
Wibowo, D., E. dan Munir, Rinaldi. (2013). Sistem Rekomendasi Jual Beli Barang dengan Memanfaatkan Metode Collaborative Filtering dan Basis Data Graf (Studi Kasus : Bukalapak . com). School of Electrical Engineering and Informatics, Institute Technology of Bandung.
Wahyo, Bambang T. dan Anggriawan, Angga W. (2015). Sistem Rekomendasi Paket Wisata Se-Malang Raya Menggunakan Metode Hybrid Content Based dan Collaborative. Jurnal Ilmiah Teknologi Informasi Asia, 9(1), 6–13.
Safitri, Marina. (Juli, 2017). Rancang Bangun Restful Web Service Pada Sistem Rekomendasi E-Commerce Berbasis Graf Neo4j dengan Metode Collaborative Filtering (Studi Kasus: Forbento). Tugas Akhir disusun untuk Memenuhi Salah Satu Syarat Memperoleh Gelar Sarjana Komputer pada Departemen Sistem Informasi Fakultas Teknologi Informasi Institut Teknologi Sepuluh Nopember, Surabaya.
Sholeh M., Rachmawati R. Y., & Susanti E. (2020). Pemodelan Basis data Graph dengan Neo4j (Studi Kasus : Basis Data Sistem Informasi Penjualan pada UMKM ). Jurnal Teknologi Informasi dan Terapan. 7(1). 25–32.
Anonim. Kesehatan. Nano Natura. [Daring]. Tersedia: https://nanotechnatura.com/kesehatan/
Anonim. Produk Kesehatan. Kalbe. [Daring]. Tersedia: https://www.kalbe.co.id/id/produk-dan-jasa/produk-kesehatan
Anonim. Pengertian E-Commerce dan Perkembangannya di Indonesia. Qwords. [Daring]. Tersedia: https://qwords.com/blog/pengertian-e-commerce/
Anonim. E-commerce: Pengertian, Jenis, dan Keuntungannya. Talenta. [Daring]. Tersedia: https://www.talenta.co/blog/insight-talenta/e-commerce/
Cung, Hoang Qui dan Jedidi, Malek. (2014). Implementing a Recommender System with Graph Database. University of Freiburg - e Business. [Daring]. Tersedia: https://diuf.unifr.ch/main/is/student-projects/thesis/implementing recommender-system-graph-database.
Ricci F., Rokach L., & Shapira, B. (2010). Recommender Systems Handbook. United States of America: Springer Science + Business Media, LLC, 233 Spring Street, New York, NY 10013.
Adiwijaya. (2016). Matematika Diskrit dan Aplikasinya. Bandung: Alfabeta. ISBN. 978-602-289-255-7.
Lawrence, K. R. (2020). Practical Gremlin - An Apache TinkerPop Tutorial. Version 283-preview, October 11th 2020. [Daring]. Tersedia: https://github.com/krlawrence/graph
Anonim. TinkerPop Documentation. Apache TinkerPop. [Daring]. Tersedia: https://tinkerpop.apache.org/docs/current/reference/#_tinkerpop_documentation
Downloads
Published
Issue
Section
License
Copyright of this journal is assigned to Jurnal Buana Informatika as the journal publisher by the knowledge of author, whilst the moral right of the publication belongs to author. Every printed and electronic publications are open access for educational purposes, research, and library. The editorial board is not responsible for copyright violation to the other than them aims mentioned before. The reproduction of any part of this journal (printed or online) will be allowed only with a written permission from Jurnal Buana Informatika.
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.