Citation

Haw, Su Cheng and Jayaram, Jayapradha and Anaam, Elham Abdulwahab (2025) A hybrid recommender model for health supplements in e-commerce. In: 4th International Conference on Computer, Information Technology and Intelligent Computing, CITIC 2024, 23 July 2024 - 25 July 2024, Virtual, Online.

Text A hybrid recommender model for health supplements in e-commerce _ AIP Conference Proceedings _ AIP Publishing.pdf - Published Version Restricted to Repository staff only Download (321kB)

Abstract

Recommender systems are important for any e-commerce platform; however, the available systems face challenges such as sparsity, cold-start issues, and also being less personalized. This is particularly true in the health supplement industry where user preferences are highly unique. This paper presents a hybrid-based recommender system as your solution to these challenges combining implicit feedback mechanisms to enhance the accuracy and relevance of recommendations. The proposed system makes use of the interaction data between the user and the product, the browsing history, purchase history, and metadata of the product to create a more adaptive recommendation system. Matrix factorization is carried out using Alternating Least Squares (ALS). Moreover, TF-IDF and Word2Vec are used to capture salient features in product descriptions. The collaborative filtering and content-based filtering recommendations are optimally combined through a weighted hybridization approach. Preliminary results show that the proposed hybrid model achieve good results: Precision@10, Recall@10, NDCG@10, MAP@10 and RMSE; 0.81, 0.75, 0.85, 0.78 and 0.85 respectively. Such improvements convey better personalization, ranking relevance, and user satisfaction

Item Type:	Conference or Workshop Item (Paper)
Uncontrolled Keywords:	Metadata, Industry
Subjects:	Q Science > QA Mathematics > QA71-90 Instruments and machines > QA75.5-76.95 Electronic computers. Computer science
Divisions:	Faculty of Computing and Informatics (FCI)
Depositing User:	Nor Afiqah Mohd Adnan
Date Deposited:	02 Dec 2025 05:55
Last Modified:	12 Dec 2025 13:22
URII:	http://shdl.mmu.edu.my/id/eprint/14933

Downloads

Edit (login required)