Authors: Jeffrey Parsons, Roman Lukyanenko, Veda C. Storey
Tags: 2018, applications, complex models, conceptual modeling, conceptual models, CRISPDM, data mining, machine learning
With the transformation of our society into a “digital world,” machine learning has emerged as an essential toolkit to extract useful information from large collections of data. However, many challenges remain for using machine learning effectively. This paper identifies and illustrates such challenges and proposes how conceptual modeling can be used to overcome some of them, as illustrated through case studies. We then examine a popular cross-industry standard process for data mining, commonly known as CRISP-DM Directions, and show the potential role that conceptual modeling can play in making each stage of this process more effective.
Cite as:
Lukyanenko R., Parsons J., and Storey V. (2018). “Modeling Matters: Can Conceptual Modeling Support Machine Learning?,” in AIS SIGSAND, Syracuse, NY, United States, May 23 – 25, 2018.
