Towards a Systematic Approach to Graph Data Modeling: Scenario-based Design and Experiences

Graph database is recently being adopted by data analytic systems as an appealing alternative to relational database for the management of large-scale inherent graph-like data. A great challenge of leveraging graph database technologies is to model a problem domain into graph. However, in the absence of considering application requirements or goals, current graph data modeling approaches seem to be invalid. This paper presents an exploration of a systematic approach for graph data modeling—SuMo. Starting from real world scenarios, requirements are transformed into a domain model, which acts as an intermediate model in SuMo, captures modeling features of that domain. SuMo defines a set of rules for the subsequent transformation of this domain model to produce a graph model. We applied SuMo to the modeling of a data-intensive analytic system using real datasets as an illustrating example to clarify our main idea. SuMo is empirically evaluated in terms of query performance, the experimental results indicate promising feasibility and efficiency. The major contribution of our work is a preliminary graph data modeling approach based on scenarios. Keywords-graph data modeling; data analytic system; scenariobased modeling; model-driven design