<![CDATA[Recommendation systems have become an essential solution in assisting users to select products that meet their needs, particularly in technology sectors such as laptop selection. This study aims to develop a more accurate recommendation system by leveraging additional attributes such as processor type, RAM capacity, and user-specific requirements, such as gaming or graphic design. The research method employs a knowledge-based approach combined with user data, enriched by purchase history and prior preferences. Testing was conducted on diverse datasets to evaluate the system's performance across various scenarios. The results demonstrate that integrating additional attributes and historical data significantly enhances the relevance of recommendations. The system is also designed with an intuitive interface to facilitate user access. These findings highlight the potential for further development, particularly in applying machine learning methods to improve personalization and recommendation accuracy.]]>
Copyrights © 2025
