The size of data available to users in online media has increased exponentially in recent years. Due to this large amount of data, people have problems processing all the available data because they do not have enough time and therefore are unable to find useful elements. So, to overcome this kind of problem, recommender system plays an important role. The system filters the data source and provides them with useful information, when this information comes in the form of suggestion the system called recommender system. An example of a recommendation system is amazon.com. Use personalized data to suggest that a user might like. RS generates a list of recommendations with different methods, including: • Collaboration-based filtering method • Content-based method • Knowledge-based method • Hybrid-based method The hierarchical model of the recommendation system is given below: Figure 1.1 Model hierarchical recommender system2. Recommendation Approaches System2.1 Collaborative Filtering (CF) Approach Collaborative filtering recommendation is a data filtering technique based on the collaboration of other users. Collaborative filtering uses the user-item matrix regardless of user or item information. Collaborative filtering is the most widely used and famous recommendation technique, widely used due to its simplicity and good results. The first recommender system, Tapestry [5], uses this collaborative filtering term and has since become widely accepted. It is based on the fact that if two users X and Y rated n items similarly or behave similarly in any environment, they will also rate or behave similarly with respect to other items. Collaborative filtering is divided into two groups: • Memory-based : Memory-based b...... middle of the sheet ...... the system requires knowing the album, the artist, the singer, the composer, etc. The content-based recommendation system fails to provide useful recommendations if the content does not include a sufficient amount of information to differentiate what the user likes from what the user does not like. 2.3 Hybrid-based recommender systemHybrid-based recommender systems combine two or more recommendation approaches to achieve better performance with fewer limitations of each individual approach. Typically, the collaborative filtering approach is combined with some other method in an attempt to remove the problems. Table 1.1 shows some of the hybrid methods that have been used Robin Burke (2002) provides seven classes of hybrid methods: weighted, switching, mixed, feature combining, feature augmentation, cascade, and meta-level. Details are shown in tabular format.