Predictive Analysis from Massive Knowledge Graphs on Neo4j – David Bader



Prof. David Bader, one of the nation’s leading experts in massive-scale graph analytics, presents a Neo4j case study on predictive analytics on a homeland security knowledge graph that connects disparate data from multiple sources such as spreadsheets and relational databases. Graphs are a natural representation for connecting information in real-world challenges such as understanding financial transactions in digital currencies, finding new communities in social networks, increasing power grid resiliency, and protecting us from cyberattack. Bader discusses his Spatio-Temporal Interaction Networks and Graphs (STING) initiative that supports new methods for finding interesting patterns and features in these critical knowledge graphs. David Bader, Chair, School of Computational Science and Engineering, Georgia Institute of Technology #KnowledgeGraphs #Neo4 #GraphConnect