6 Session-based recommendation
This chapter covers
- How to implement recommendation systems using session data
- How to design graph models for session-based recommendation engines
- How to import existing datasets into the graph models designed
The previous two chapters introduced two of the most common approaches to implementing recommendation engines: the content-based and collaborative filtering approaches. The advantages of each were highlighted, but several drawbacks also emerged during the discussion. Notably, these recommendation techniques require information about users that is not always available. This chapter covers another approach to recommendations that is useful when it is difficult or impossible to get access to user interaction history or other details about the users. In such cases, applying the classic approaches would not produce good results.
6.1 The session-based approach
Suppose you would like to build a recommendation engine for an online travel site offering lodging reservations that doesn’t require login or registration in the early stages of the process. Using a session-based recommendation engine it is possible to deliver recommendations even in cases like these, where little about the user is known.