Using graphs for recommendations
3 likes5,576 views
This document contains a presentation on using graph databases for recommendations. It begins with an introduction to graphs and graph theory, then discusses what graph databases are and how they are different from relational databases. It explains how graphs are well-suited for complex querying and representing connected data. The presentation describes how recommendation systems work and how graph algorithms and storing recommendation data in a graph structure provide benefits like real-time recommendations, navigating relationships between items, and efficient operations. It concludes with a demonstration, examples, and discussing future events.
Using graphs for recommendations
- 1. Data Science in Marke-ng [email protected] @rvanbruggen
- 2. Graphs for Recommenda-ons [email protected] @rvanbruggen
- 3. Agenda • About Graphs • About Graph Databases • Why Graph Databases ma=er for Recommenda?ons – Short demonstra?on • Case Studies • Q&A
- 6. Meet Leonhard Euler • Swiss mathema?cian • Inventor of Graph Theory (1736)
- 7. Königsberg (Prussia) -‐ 1736
- 8. A B D C
- 9. A B D C 1 2 3 4 7 6 5
- 11. So what is a graph database? • OLTP database – “end-‐user” transac?ons • Model, store, manage data as a graph
- 12. What is a graph? Node Rela?onship
- 13. Contrast with Rela?onal Graphs are often referred to as “Whiteboard Friendly”. The data model reflects the way a domain expert would naturally draw their data on a whiteboard “The schema is the data”. Schema flexibility allows the system to change in response to a changing environment
- 14. What are graphs good for? Complex Querying
- 15. Examples of complex queries? 1. Semi-‐structure in datasets 1 – Normaliza?on introduces complexity – Forces developers to develop all kinds of logic to deal with this variability in their applica?on logic
- 16. Examples of complex queries: 2. Connectedness in data Lots of normalized rela?onships between the different en??es, forces developers to do • Deep joins • Recursive joins • Pathfinding opera?ons • “open-‐ended” queries
- 19. Recommender system • Not new • Prime BI applica?on – Mining data – Calcula?ng recommenda?ons / promo?ons in batch – Presen?ng these to the user online / offline 1
- 21. Graphs in Recommender Systems • Real ?me aspect • Recommenda?on Prac?ces rely on Graph Algorithms • Opera?onal efficiency
- 22. Real -me recommenda?ons? • Context is everything – You don’t want to be recommending a fitness subscrip?on when you have just been admi=ed to hospital… • Relevance is King – More ‘s?cky’ applica?ons – Increase user sa?sfac?on – Drive traffic: get users to do more stuff with your applica?on
- 23. Recommenda?on prac?ces: Graph Algorithms ● Helpful for naviga?ng complex networks ● tell me how A and B are related ● The things on the path between A and B could very well be interes?ng ● ShortestPath, AllShortestPaths, Weighted ShortestPath (Dijkstra, A*) ● Helpful for understanding the important parts of a network ● Clusters ● Bridges ● Centrality ● Betweenness Centrality ● (Page)Ranking
- 24. Recommenda?on prac?ces: Making triangles ● Close the triangle to make a recommenda?on ● Olen looking for “missing links” ● e.g. making a recommenda?on of movies based on what similar users have enjoyed
- 25. Opera-onal Efficiency • Graph datamodel removes the need for many “batch opera?ons” – No need to precalculate – just feed it into the graph • Complex pa=ern matching in milliseconds • Graph Locality == Predictability Speed, even over large datasets
- 26. Short demo
- 30. Neo4j versions / licenses Neo4j License Overview Developer! Seats! Personal Startup / Departmental Enterprise deployment models ($6K*/Developer/Year) Test! Instances! ($6K/Instance/Year) Production! Instances! (Bundle / Core Pricing) Open source Commercial license terms available Specific OEM models Instances whose purpose is to ensure that the software accessing Neo4j is meeting specification.! ! (e.g. System Test, Integration Test, UAT, Performance Test, Staging) Instances that store and process data in a way that benefits and advances an organization’s goals.! ! May be accessed by applications and/or end users Includes access by programmers to licensed test instances, and private instances on the programmer’s personal machine for the sole purpose of writing, debugging, or testing software designed to access Neo4j *Or otherwise, depending on the Bundle, and negotiation
- 31. Future trainings events! 3
- 32. Conway Hall, November 13th bit.ly/graphday
- 33. QA, Conclusion, Next Steps Neo Technology www.neotechnology.com Neo4j www.neo4j.org [email protected] or +32 478 686800