Deeper Insight with Graph Analysis and Machine Learning
Both graph analysis and machine learning can be used very effectively to detect patterns, similarities and anomalies in datasets. The former is particularly useful when data can be represented as a network in which the connectedness of data, ie. the explicit relationships between entities, play a role. Social network analysis is one obvious example, but the approach is applicable to a wide range of use cases in e-commerce, fraud detection, cyber security, and so on.
In this session, we will show that graph analysis and machine learning are complementary techniques. We will describe how to create, manage and analyze graph data with Oracle technologies and how to visualize results of graph processing. For the integration of machine learning, we will explain how to convert graph data into a vector, preserving the topology of the graph as far as possible. To illustrate the approach, we will use two scenarios. Firstly, we will determine suspicious behavior in a medical services dataset, and secondly, we will present a customer segmentation use case. Finally, we will explain how the entire environment can be deployed on the Oracle Cloud.