Personalized Recommendations of Products to Users

Many organizations utilize recommendation systems to increase their profitability and win over customers, including Facebook, which suggests friends, LinkedIn, promotes employment, Spotify, recommends music, Netflix, movies, Amazon, purchases. When it comes movie system, suggestions are made based on user similarities (collaborative filtering) or by considering a specific user's behavior (content-based that he she wishes interact with. Using TF-IDF, cosine similarity method for content-based filtering, deep learning collaborative approach, this study compares two system. The proposed evaluated calculating the precision recall values. On small dataset, filtering methodology had of 5.6% whereas approach 57%. Collaborative clearly worked better than filtering. Future improvements involve creating single hybrid system combines improve outcomes.