Graph Databases are naturally well-suited for building recommendation engines. In this talk, Michal will share his experience building a number of high-performance production-ready recommendation engines using Neo4j and introduce the open-source GraphAware Recommendation Engine Library, which enables Java developers to rapidly build their own recommender systems.
This presentation starts by a brief explanation of why graphs are a suitable data model for building recommender systems. A summary of typical recommendation engine requirements follows, including the business and technical challenges these requirements introduce. Afterwards, the talk dives into possible solutions of these challenges, both from business and architectural/design perspectives, and introduces the GraphAware Recommendation Engine Library.
What follows is a demonstration of how this open-source recommendation engine skeleton solves many of the issues and how it handles the "plumbing", so that developers can focus on expressing the business logic specific to their domain.
The talk concludes by presenting complexities yet to be solved, and a brief survey of alternative approaches.
A majority of examples in this talk are drawn from real-world use cases and the speaker's personal experience building recommendation engines. Attendees should have a very basic understanding of graph theory. Prior experience with Neo4j and the Cypher query language is a plus, but not necessary. Ability to read Java is recommended.
Attendees will learn:
* what is a recommendation engine and what it is good for
* why graphs are a good fit for building one
* what business and technical challenges one faces building a recommender
* what possible solutions there are for these challenges
* how to build a high-performance graph-based recommendation engine in minutes
* real-world case studies
