Graph Networks for Predictive Analytics

Interesting thought here. We used graph network methods for years to understand and optimize supply chains. It is also useful because it can show the relationship between competing entities. Its also a useful way to present analytical structures to the decision makers.


Predictive Analytics: Benefits and Challenges of Using Graph Theoretic Methods

Leveraging Contextual Network Information for Better Accuracy
by Nick Lim

practice of predictive analytics has come a long way since the advent of operations research. Current predictive models routinely use more than 100 variables, most of them are characteristics of the object being analyzed, including age and gender for customer analysis, or color and text for advertisements. In this article, we will explore how graph methods can be used in predictive analytics .... "