Content-based Recommendation Engine for Video Streaming Platform
Puskal Khadka, Prabhav Lamichhane
TL;DR
This paper addresses the challenge of presenting relevant video recommendations in large streaming catalogs by adopting a content-based approach that relies on item metadata. It constructs TF-IDF representations from features such as Genre, Cast, and Overview, and uses cosine similarity to quantify item likeness for personalized suggestions. A user-centric evaluation on a small dataset yields precision ~0.91, recall ~0.83, and F1 ~0.87, demonstrating the method's effectiveness when user data is sparse. The approach offers fast, personalized recommendations without requiring cross-user data, and the authors discuss extending it with hybrid signals and deep language embeddings to further improve performance.
Abstract
Recommendation engines suggest content, products, or services to the user by using machine learning algorithms. This paper proposes a content-based recommendation engine that provides personalized video suggestions based on users' previous interactions and preferences. The engine uses TF-IDF (Term Frequency-Inverse Document Frequency) text vectorization technique to evaluate the relevance of words in video descriptions, followed by the computation of cosine similarity between content items to determine their degree of similarity. The system's performance is evaluated using precision, recall, and F1-score metrics. Experimental results demonstrate the effectiveness of content-based filtering in delivering relevant and personalized video recommendations to users. This approach can enhance user engagement on video streaming platforms and reduce search time, providing a more intuitive, preference-based viewing experience.