Perancangan Sistem Rekomendasi Pemilihan Mobil Bekas Kategori MPV dan City Car Menggunakan K-Nearest Neighbor (K-NN) dengan Hybrid Filtering
DOI:
https://doi.org/10.36312/qrfc5h79Keywords:
Sistem Rekomendasi, Mobil Bekas, K-Nearest Neighbor, Hybrid FilteringAbstract
Perkembangan kebutuhan transportasi pribadi di Indonesia menunjukkan tren yang terus meningkat, terutama di wilayah perkotaan. Di Kota Padang, meningkatnya kebutuhan tersebut diikuti oleh semakin banyaknya pilihan mobil bekas kategori MPV dan City Car, namun banyaknya alternatif pilihan ini justru menimbulkan information overload bagi calon pembeli. Penelitian ini bertujuan merancang dan mengimplementasikan sistem rekomendasi berbasis website menggunakan metode K-Nearest Neighbor (K-NN) dengan pendekatan Hybrid Filtering. Metode pengembangan sistem yang diterapkan adalah model Waterfall. Pendekatan Hybrid Filtering menggabungkan Content-Based Filtering dan Collaborative Filtering, sementara algoritma K-NN digunakan untuk menghitung tingkat kemiripan antar data kendaraan berdasarkan atribut seperti harga, tahun produksi, dan spesifikasi teknis menggunakan Euclidean Distance. Sistem juga menerapkan mekanisme pre-filtering berdasarkan kategori kendaraan untuk mengurangi kompleksitas perhitungan KNN agar sistem tetap responsif. Hasil pengujian fungsional menggunakan Black Box Testing menunjukkan seluruh fitur sistem berjalan dengan baik. Pengujian akurasi menghasilkan nilai Precision rata-rata sebesar 0,78, Recall 0,83, dan Mean Absolute Error (MAE) sebesar 0,15. Simpulannya, sistem ini mampu memberikan rekomendasi yang akurat, relevan, serta membantu mempercepat proses pengambilan keputusan calon pembeli mobil bekas.
The development of private transportation needs in Indonesia shows a continuously increasing trend, especially in urban areas. In Padang City, this growth is followed by various used car options in the MPV and City Car categories, yet these alternatives cause information overload for potential buyers. This research aims to design and implement a web-based recommendation system using the K-Nearest Neighbor (K-NN) method with a Hybrid Filtering approach. The system development method applied is the Waterfall model. The Hybrid Filtering approach combines Content-Based Filtering and Collaborative Filtering, while the K-NN algorithm calculates similarity levels between vehicle data based on attributes such as price, production year, and technical specifications using Euclidean Distance. The system also applies a pre-filtering mechanism based on vehicle categories to reduce K-NN computational complexity and maintain responsiveness. Functional testing results using Black Box Testing indicate that all system features operate correctly. Accuracy testing produced an average Precision value of 0.78, a Recall of 0.83, and a Mean Absolute Error (MAE) of 0.15. In conclusion, this system provides accurate and relevant recommendations, helping potential used car buyers accelerate their decision-making process.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Rudi Kurnia Al Amin, Yeka Hendriyani, Delvi Asmara, Yulia Fatmi

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with Journal of Authentic Research agree to the following terms:
- For all articles published in Journal of Authentic Research, copyright is retained by the authors. Authors give permission to the publisher to announce the work with conditions. When the manuscript is accepted for publication, the authors agrees to implement a non-exclusive transfer of publishing rights to the journals.
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution-ShareAlike 4.0 International License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.