Customer Journey Analytics using Neo4j Graph Platform
summary
Shows that Neo4j stores native property graphs and can turn event logs into actionable links: three supermarket purchases by one customer lead to an inferred roast‑chicken “likes” relationship created with MERGE and strength attribute, shoppers get classified (example: pantry stuffer) and a favourite store assigned so marketing can target those affected by a McKinnon flood. Uses Cypher, APOC, Kafka and Graph Data Science algorithms for path analysis (monthly statement chains) to predict non‑renewal; scales to billions of nodes on a single instance.
AI-written summary · about
chapters (13)
- 0:00Neo4j and customer journey analytics
- 1:24Graphs in Neo4j
- 3:51Relationships as data
- 5:17Cypher queries
- 7:03Why customer journey analytics
- 8:07Customer behavior insights
- 10:12Shopper type classification
- 11:16Proactive outreach with relationships
- 12:39Telco churn prediction
- 13:41Data science in Neo4j
- 15:48Loading data into Neo4j
- 16:52Neo4j resources
- 17:13Q&A on Cypher
related talks
32mUnderstanding Complexly Connected Data using Graph Databases
14mApplying Neo4j to Multilevel Marketing Companies
18mGraph analytics: From zero to hero
01h 41mGraph Intelligence: Enhance Reasoning and Retrieval Using Graph Analytics
38mRecommendation Engine with Neo4j, Piece of Cake
27mConnecting the Dots: Graph Analytics for Economic Sustainability
56mGraph Analytic Systems
53mBreaking Credit Card Fraud Rings with Neo4j