Kohesi: Jurnal Sains dan Teknologi

Articles

Vol. 10 No. 6 (2025): Kohesi: Jurnal Sains dan Teknologi, ISSN 3025-1311

KAJIAN LITERATUR COLD START PROBLEM PADA SISTEM REKOMENDASI E-COMMERCE : TANTANGAN DAN STRATEGI PENANGANANNYA

Submitted
November 13, 2025
Published
2025-11-13

Abstract

rekomendasi yang mampu memberikan saran relevan meski dengan keterbatasan data awal. Namun, munculnya pengguna baru, item baru, atau ekspansi ke pasar lintas bahasa menyebabkan munculnya cold-start problem yang menurunkan akurasi dan kinerja sistem rekomendasi. Kajian ini menggunakan metode systematic literature review terhadap berbagai penelitian tahun 2020–2025 yang membahas strategi penanganan cold-start pada sistem rekomendasi e-commerce. Hasil analisis menunjukkan bahwa pendekatan yang digunakan mencakup pemanfaatan side-information, graph-based embedding, meta-learning, reinforcement learning (LTV-aware), serta integrasi retrieval augmentation dengan Large Language Model (LLM). Setiap metode memiliki keunggulan dan keterbatasan: side-information efektif dengan metadata kaya, graph-based unggul pada sistem bertaxonomy, meta-learning cepat beradaptasi dengan sedikit data, sedangkan reinforcement learning dan LLM augmentation mampu mengoptimalkan nilai jangka panjang serta meningkatkan relevansi lintas bahasa. Kajian ini menyimpulkan bahwa tren penelitian terkini bergerak ke arah model hibrida yang menggabungkan berbagai pendekatan untuk menciptakan sistem rekomendasi yang adaptif, efisien, dan berkelanjutan.

References

  1. Al Ghifari, N. T., Sitohang, B., & Saptawati, G. A. P. (2021). Addressing Cold Start New User in Recommender System Based on Hybrid Approach: A Review and Bibliometric Analysis. IT Journal Research and Development (ITJRD), 6(1).
  2. Ji, L., Qin, Q., Han, B., & Yang, H. (2021). Reinforcement Learning to Optimize Lifetime Value in Cold-Start Recommendation. Proceedings of the 30th ACM International Conference on Information and Knowledge Management (CIKM ’21). ACM.
  3. Liu, S., Liu, Y., Zhang, X., Xu, C., He, J., & Qi, Y. (2023). Improving the Performance of Cold-Start Recommendation by Fusion of Attention Network and Meta-Learning. Electronics, 12(2), 376.
  4. Maksimov, I., Rivera-Castro, R., & Burnaev, E. (2020). Addressing Cold Start in Recommender Systems with Hierarchical Graph Neural Networks. arXiv preprint arXiv:2009.03455.
  5. Panteli, A., & Boutsinas, B. (2023). Addressing the Cold-Start Problem in Recommender Systems Based on Frequent Patterns. Algorithms, 16(4), 182.
  6. Snell, J., Swersky, K., & Zemel, R. (2017). Prototypical Networks for Few-Shot Learning. Advances in Neural Information Processing Systems (NeurIPS).
  7. Wang, H. (2021). ZeroMat: Solving Cold-start Problem of Recommender System with No Input Data. arXiv preprint arXiv:2112.03084.
  8. Wang, Y., Chen, Y., Li, H., Xu, C., Luo, Y., Mao, X., Li, C., Du, L., Ma, C., Jiang, Q., Wang, Y., Gao, F., Mo, W., Wen, P., Kumar, S., Park, T., Song, Y., Rajaram, V., Cheng, T., Durgia, S., Kolari, P., & Rajaram, V. (2025). CSRM-LLM: Embracing Multilingual LLMs for Cold-Start Relevance Matching in Emerging E-Commerce Markets. Proceedings of the 34th ACM International Conference on Information and Knowledge Management (CIKM ’25). ACM.
  9. Zhang, Y., Maekawa, T., & Hara, T. (2021). Using Social Media Background to Improve Cold-Start Recommendation Deep Models. arXiv preprint arXiv:2106.02256.
  10. Zhou, G., Zhu, X., Song, C., Fan, Y., Zhu, H., Ma, X., Yan, Y., Jin, J., Li, H., & Gai, K. (2018). Deep Interest Network for Click-Through Rate Prediction. Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD ’18), 1059–1068.

Most read articles by the same author(s)

1 2 3 4 > >> 

Similar Articles

21-30 of 240

You may also start an advanced similarity search for this article.