Abstract
Current movie recommendation systems often struggle to capture complex user preferences and dynamics, primarily relying on content-based or collaborative filtering techniques. This research introduces a novel deep learning-powered method to enhance movie recommendation models, addressing the limitations of existing systems. By analyzing user behavior records and utilizing movie content elements, our method guarantees the greatest degree of customisation. In this study, we employ Artificial Intelligence (AI), graph-based techniques, and text mining to accurately estimate user preferences. While PageRank ranks the films based on their importance in the individual's history of surfing, Convolutional Neural Network (CNN) predicts the possibility that the movie would be accepted. The experiments employed a dataset of 215 users' browsing activity in 508 movie pages for evaluation. The presented approach achieved significant enhancement in recommendation precision and recall metrics resulting in 7.15% precision expansion and 5.19% recall growth which indicates its potential implementation in personalized movie recommendation systems.