<![CDATA[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.]]>
