Perancangan Sistem Rekomendasi Pemilihan Model
Keywords:
Artificial Intelligence, Content-Based Filtering, Cosine Similarity, Sistem Rekomendasi, Platform AI.Abstract
Perkembangan teknologi Artificial Intelligence (AI) yang semakin pesat menghadirkan berbagai model AI dengan karakteristik dan kemampuan yang berbeda-beda sehingga pengguna sering mengalami kesulitan dalam menentukan model yang paling sesuai dengan kebutuhannya. Penelitian ini bertujuan untuk merancang sistem rekomendasi pemilihan platform Artificial Intelligence menggunakan metode Content-Based Filtering (CBF) berdasarkan kemiripan karakteristik setiap model AI. Dataset penelitian terdiri atas 40 model AI yang direpresentasikan menggunakan enam atribut, yaitu Context Window, Intelligence Index, Price, Speed (Token/s), Latency, dan End-to-End Response Time. Sebelum dilakukan proses perhitungan, seluruh atribut dinormalisasi menggunakan metode Min-Max Normalization untuk menyamakan rentang nilai data. Selanjutnya, tingkat kemiripan antar model dihitung menggunakan metode Cosine Similarity dan diurutkan berdasarkan nilai similarity tertinggi. Hasil penelitian menunjukkan bahwa model MiMo-V2-Omni-0327 memperoleh nilai similarity tertinggi sebesar 0,9945 terhadap model acuan MiMo-V2-Omni, diikuti oleh Step 3.7 Flash, MiniMax-M3, MiMo-V2.5-Pro, dan DeepSeek V4 Pro (High). Hasil tersebut menunjukkan bahwa metode Content-Based Filtering yang dipadukan dengan Cosine Similarity mampu menghasilkan rekomendasi model Artificial Intelligence berdasarkan kemiripan karakteristik setiap model sehingga dapat membantu pengguna dalam memilih platform AI yang sesuai dengan kebutuhannya.
References
[1] A. Analysis, “Artificial Analysis,” Artificial Analysis. Accessed: Jul. 10, 2026. [Online]. Available: https://artificialanalysis.ai/
[2] W. X. Zhao et al., “A Survey of Large Language Models,” pp. 1–144, 2026.
[3] P. Khurana and S. Parveen, “Approaches of Recommender System : A Survey,” vol. 34, no. 3, pp. 134–138, 2016.
[4] C. Fiarni, H. Maharani, and N. Calista, “Product Recommendation System Design Using Cosine Similarity and Content-based Filtering Methods,” vol. 3, no. 2, pp. 42–48, 2019.
[5] U. Javed, K. Shaukat, I. A. Hameed, F. Iqbal, T. M. Alam, and S. Luo, “A Review of Content-Based and Context-Based Recommendation Systems,” pp. 274–306.
[6] F. Ramadhan and A. Musdholifah, “Online Learning Video Recommendation System Based on Course and Sylabus Using Content-Based Filtering,” vol. 15, no. 3, pp. 265–274, 2021.
[7] M. N. Arkan, A. P. Widodo, and G. Aryotejo, “A Web-Based Tourism Recommendation System for Boyolali Using Content-Based Filtering and Cosine Similarity,” vol. 17, no. April 2025, 2026, doi: 10.14710/jmasif.17.1.72520.
[8] V. Boppana and P. Sandhya, “Web crawling based context aware recommender system using optimized deep recurrent neural network,” J. Big Data, 2021, doi: 10.1186/s40537-021-00534-7.
[9] M. F. Abdurrafi, D. Handayani, and U. Ningsih, “Content-based filtering using cosine similarity algorithm for alternative selection on training programs,” pp. 204–212, 2023.
[10] T. Ridwansyah, B. Subartini, and S. Sylviani, “Penerapan Metode Content-Based Filtering pada Sistem Rekomendasi,” vol. 4, no. 2, 2024.
[11] M. Casillo, F. Colace, D. Conte, M. Lombardi, D. Santaniello, and C. Valentino, “Context ‑ aware recommender systems and cultural heritage : a survey,” J. Ambient Intell. Humaniz. Comput., vol. 14, no. 4, pp. 3109–3127, 2023, doi: 10.1007/s12652-021-03438-9.
[12] A. Rianti, N. Wachid, A. Majid, and A. Fauzi, “Machine learning journal article recommendation system using content based filtering,” pp. 1–10, 2020.
[13] Y. S. Anggraeni, S. D. Saputri, T. Azzahra, A. G. Verrel, and I. Artikel, “Implementasi Content-Based Filtering Menggunakan TF-IDF dan Cosine Similarity untuk Rekomendasi Buku Akademik Mahasiswa,” vol. 11, no. 2, pp. 213–225, 2026, doi: 10.30591/jpit.v11i2.10055.
[14] F. Christyawan, A. N. Rohman, and A. D. Hartanto, “Application of Content-Based Filtering Method Using Cosine Similarity in Restaurant Selection Recommendation System,” vol. 6, no. 3, pp. 1559–1576, 2024, doi: 10.51519/journalisi.v6i3.806.
[15] S. Qassimi, E. H. Abdelwahed, M. Hafidi, and A. Qazdar, “Towards a folksonomy graph ‑ based context ‑ aware recommender system of annotated books,” J. Big Data, 2021, doi: 10.1186/s40537-021-00457-3.
