The rapid growth of digital libraries and online bookstores has created a challenge for users to identify books that match their interests. A recommendation system helps users discover relevant content by analyzing patterns in user behavior and item characteristics. This paper presents a Book Recommendation System developed using Machine Learning techniques to provide personalized suggestions based on user preferences and historical ratings. The system uses a dataset obtained from Kaggle containing information such as book titles, authors, and user ratings. Data preprocessing techniques are applied using Python libraries such as Pandas and NumPy to clean and structure the data. Visualization tools such as Matplotlib and Seaborn are used to understand rating distributions and user interactions. Collaborative filtering and content‑based filtering techniques are implemented to generate accurate recommendations. A pivot table is constructed to represent the relationship between users and books, and cosine similarity is used to measure similarity between items. Sparse matrices and Scikit‑learn libraries are utilized to improve computational efficiency. Experimental results show that the system successfully provides relevant book recommendations and improves the user experience by reducing the effort required to search for suitable books. The proposed system demonstrates the practical application of machine learning in personalized digital content recommendation platforms.