Neo4j Live Demo: Graph Recommendation Systems
Have you ever considered using data relationships to improve machine learning (ML)?
If so, join us for a 30-minute demo on how to use Neo4j Graph Data Science to build a recommendation engine with graph technology.
Relationships are highly predictive of behavior, yet most data science models neglect this information because it’s difficult to extract at scale from relational databases. With graphs, relationships are embedded in the data itself, making it easier to add predictive capabilities to your existing practices and automate your analytical model building.
Making relevant recommendations requires the ability to correlate product, customer, inventory, and logistics data. A graph database tracks these relationships with ease, and we’ll show you how with a real-life example.
In this demo, we’ll walk you through:
- Using graph-based feature engineering to uncover predictive patterns
- Analyzing a real dataset of news recommendations with 17.5 million click events
- Personalizing to each user with rank-ordered recommendations
Register today to learn graph data science techniques from Neo4j experts so you can create your own recommendation engine!

David Allen is Technology Partner Architect at Neo4j. He is a deeply technical generalist with experience in managing teams and driving towards complex goals. The most fun he has had in his career is when he is learning something new, or trying to figure out how to do something that hasn’t been done before.


||text_203395||
Sed ac purus sit amet nisl tincidunt tincidunt vel at dolor. In ullamcorper nisi risus, quis fringilla nibh mattis ac. Mauris interdum interdum eros, eget tempus lectus aliquet at. Suspendisse convallis suscipit odio, ut varius enim lacinia in. Lorem ipsum dolor sit amet, consectetur adipiscing elit.
Sed ac purus sit amet nisl tincidunt tincidunt vel at dolor. In ullamcorper nisi risus, quis fringilla nibh mattis ac. Mauris interdum interdum eros, eget tempus lectus aliquet at. Suspendisse convallis suscipit odio, ut varius enim lacinia in. Lorem ipsum dolor sit amet, consectetur adipiscing elit.
Sed ac purus sit amet nisl tincidunt tincidunt vel at dolor. In ullamcorper nisi risus, quis fringilla nibh mattis ac. Mauris interdum interdum eros, eget tempus lectus aliquet at. Suspendisse convallis suscipit odio, ut varius enim lacinia in. Lorem ipsum dolor sit amet, consectetur adipiscing elit.