IMPROVING RECOMMENDATION SYSTEM PERFORMANCE WITH EVENT-BASED TEMPORAL DATA MODEL

Recommendation Systems (RS) are systems that propose products for customers to view. Since the turn of the millennium, these kinds of technologies have been increasingly common, and now almost all online apps use them to make suggestions to their users in an effort to keep and increase their engagement with the apps. The challenge of idea generation is tackled in a variety of ways by the various RS kinds. These strategies have progressed to the point where both complicated and straightforward algorithms can be used to implement them. In spite of the availability of numerous recommendation algorithms, some may be more suitable than others for specific tasks. This paper discusses a variety of recommendation algorithms, some of which are quite complex.