Authors: Eric Yu, Soroosh Nalchigar
Tags: 2018, conceptual modeling
The effective development of advanced data analytics solutions requires tackling challenges suchas eliciting analytical requirements, designing the machine learning solution, and ensuring thealignment between analytics initiatives and business strategies, among others. The use of con-ceptual modeling methods and techniques is seen to be of considerable value in overcoming suchchallenges. This paper proposes a modeling framework (including a set of metamodels and a set ofdesign catalogues) for requirements analysis and design of data analytics systems. It consists ofthree complementary modeling views: business view, analytics design view, and data preparationview. These views are linked together to connect enterprise strategies to analytics algorithms andto data preparation activities. The framework includes a set of design catalogues that codify andrepresent an organized body of business analytics design knowledge. As thefirst attempt to val-idate the framework, three real-world data analytics case studies are used to illustrate theexpressiveness and usability of the framework. Findings suggest that the framework provides anadequate set of concepts to support the design and implementation of analytics solutions.Read the full paper here: https://reader.elsevier.com/reader/sd/pii/S0169023X18301691?token=C3CC80182043915D7F7EFD9F87FFDC88BF0BAD98982FFCC49BCC7F9C67F7AAE02266241E086D9145D9940855B4E096E9
