Ted-Talks Recommendation System using ML Algorithms

This research presents the TED Talks Recommendation System, aimed at enhancing user experience through personalized recommendations. It tackles the challenge of providing tailored suggestions with limited data for new users and an ever-growing content library. Seven advanced recommendation algorithms are explored: K-means Clustering, Matrix Factorization, Nearest Neighbors, Restricted Boltzmann Machines, Clustering with Locality-Sensitive Hashing (LSH), and Association Rules. The performance of each algorithm is evaluated in terms of suitability, diversity, and scalability. The results show that K-means is effective in identifying patterns, while matrix factorization leads to better results than the integration filter. Nearest Neighbors provides adaptability and Restricted Boltzmann Machines model complex user interactions. LSH enhances scalability, and Association Rules offer interpretability through content associations. This study demonstrates the potential for developing robust recommendation systems tailored to the TED Talks ecosystem, ultimately improving user engagement and satisfaction.