| dc.description.abstract | The e-commerce websites are growing and have shown no sign of stopping in recent
years. This project resolves the limitations of existing recommendation systems on ecommerce websites, focusing on the enhancement of personalized product suggestions.
The aim is to build a recommendation system that takes advantage of machine learning approaches, particularly the collaborative filtering method. By doing this, it seeks
to generate extremely customized product recommendations using user behavior, preference, and rate item data. Overcoming the inadequacies of the initial proposals creates
a distinctive and exciting shopping experience for customers. As such, it enhances customer satisfaction as well as contributes to high sales turnovers. To create a visually
appealing and user-friendly project, the application of HTML, CSS, and JavaScript is
necessary. HTML provides the basic structure of a web page, while CSS is used to
style and format the content material. JavaScript allows dynamic capability which includes interactive menus, animations, and form validation. In addition, Spring Boot, a
popular Java-based framework, is utilized for constructing the lower back-cease of the
internet site. It gives a complete set of equipment and features that enable builders to
quickly create and install sturdy, scalable, and maintainable packages. By leveraging
that technology, the website will become smooth to navigate, visually attractive, and
offer unbroken user enjoyment. The source code for this thesis is always available at:
https://github.com/hduy2001/Thesis | en_US |
