COMPARATIVE STUDY OF EMBEDDING-BASED RECOMMENDATION METHODS FOR AN ONLINE PERFUME STORE

Abstract

In modern e-commerce, recommender systems are an important tool for personalization and decision support. With the growth of data volumes, the search for relevant products becomes more difficult, especially in areas such as perfumery, where the choice depends on subjective factors. Traditional approaches often do not provide sufficient accuracy.

References

1. Zhang, Y., Feng, F., Zhang, J., Bao, K., Wang, Q., & He, X. (2025) CoLLM: Integrating Collaborative Embeddings Into Large Language Models for Recommendation. IEEE Transactions on Knowledge and Data Engineering, 37(5), 2329–2340. Retrieved from: https://doi.org/10.1109/TKDE.2025.3540912.
2. Li, X. (2025) Design of a Web Content Personalized Recommendation System Based on Collaborative Filtering Improved by Combining k-Means and LightGBM. Journal of Web Engineering, 24(2), 267–290. Retrieved from: https://doi.org/10.13052/jwe1540-9589.2425.
3. Çano, E., & Morisio, M. (2019) Hybrid recommender systems: A systematic literature review. Intelligent Data Analysis, 21, 1487–1524. Retrieved from: https://doi.org/10.3233/IDA-163209.
4. Smelyakov, K., Karachevtsev, D., Kulemza, D., Samoilenko, Y., Patlan, O., & Chupryna, A. (2020) Effectiveness of Preprocessing Algorithms for Natural Language Processing Applications. 2020 IEEE International Conference on Problems of Infocommunications. Science and Technology (PIC S&T), 187–191. Retrieved from: https://doi.org/10.1109/PICST51311.2020.9467919.
5. Xia, P., Zhang, L., & Li, F.-Z. (2015) Learning similarity with cosine similarity ensemble. Information Sciences, 307, 39–52. Retrieved from: https://doi.org/10.1016/J.INS.2015.02.024