The emergence of online books has sparked fierce competition, prompting the utilization of recommender systems to enhance user experiences. These systems aid users in product recommendations and preference insights, driving revenue growth through efficient customer engagement. This study introduces a comprehensible approach to book recommendations, facilitating optimal book selection for readers. The methodology relies on database training and user feedback to furnish insightful information, facilitating well-informed decisions. The proposed system employs the collaborative filtering technique, leveraging machine learning through the K-Nearest Neighbors (KNN) model to classify books based on user preferences. This paper outlines the architecture of the recommended system, showcasing its practical implementation. By integrating collaborative filtering and machine learning, the methodology presents a potent solution for enhancing user interactions, fostering book discovery, and ultimately boosting revenue for online books.

 Keywords: — KNN.