A Methodology to Identify Alternative Suitable NoSQL Data Models via Observation of Relational Database Interactions

The effectiveness and performance of data-intensive applications are influenced by the data models upon which they are built. The relational data model has been the de facto data model underlying most database systems since the 1970's, but the recent emergence of NoSQL data models have provided users with alternative ways of storing and manipulating data. Previous research demonstrated the potential value in applying NoSQL data models in non-distributed environments. However, knowing when to apply these data models has generally required inputs from system subject matter experts to make this determination. This research considers an existing approach for selecting suitable data models based on a set of 12 criteria and extends it with a novel methodology to characterize and assess the suitability of the relational and NoSQL data models based solely on observations of a users interactions with an existing relational database system. Results from this work show that this approach is able to identify and characterize the pre-established criteria in the observed usage of existing systems and produce suitability recommendations for alternate data models.