Graph Algorithms in SQL
Community Detection Algorithm (Louvain)
The Community Detection algorithm is used to detect communities (clusters) in networks (interrelated items) by evaluating how much more densely connected the nodes within a community are, compared to how connected they would be in a random network (i.e., nodes more like each other than to the other nodes). Timbr’s GA library includes the popular Louvain community detection algorithm.
Network of Connected Entities
Entities clustered into communities
Sample use cases
Detecting communities for targeted advertising
Identifying stock groups whose share price is affected by same events
Suggesting relevant communities based on interests, behavior, etc.
Recommending health practitioners based on their ranking
Recommending products based on product-groups relavent to specific types of customers