Original Title: Conceptual Modelling and Machine Learning: Coexistence, Competition or Mutual Complementation?

Conceptual Modelling and Machine Learning: Coexistence, Competition or Mutual Complementation?

Type:
  • Master Thesis Business Information Systems
Status:
offered
Tutor:

Abstract

Motivation

Software engineering is based on the idea to develop a specification of a software system that satisfies certain requirements. To analyse requirements and to support the specification of software systems, conceptual models are of pivotal relevance. They do not only allow abstracting peculiarities of specific implementation issues away, they also bridge the gap between formal representations and domain languages. This traditional conception of software development is fundamentally challenged by machine learning approaches to automation. Instead of defining a problem specification, an inductive approach is taken to generate a system that is tested against a given set of problem instances. Such an approach seems especially appealing, because it allows the development of software without the need to develop costly conceptual models. However, while machine learning has produced impressive results in some areas such as image recognition, it is the question whether it can be applied to areas such as business information system where conceptual modeling is the approach of choice. This thesis targets an ambitious topic. Its aim is threefold, that is, to analyse whether there are problems that require either one or the other approach and how conceptual modelling and machine learning could support each other.

Literature

Brodie, M. L., Mylopoulos, J., & Schmidt, J. (Eds.) (1984). On Conceptual Modelling: Perspectives from Artificial Intelligence, Databases, and Programming Languages. Berlin, Heidelberg, New York: Springer.

Domingos, P. (2017). The Master Algorithm: How the Quest for the Ultimate Learning Machine Will Remake Our World. London: Penguin Books Ltd.

Embley, D. W., & Thalheim, B. (Eds.) (2011). Handbook of Conceptual Modeling. Berlin, Heidelberg: Springer.

Murphy, K. P. (2012). Machine learning: A probabilistic perspective. Adaptive computation and machine learning series: MIT Press.

Frank, U. (2011). Multi-Perspective Enterprise Modelling: Background and Terminological Foundation (ICB Research Report No. 46). Retrieved from ICB University of Duisburg-Essen, Campus Essen website: www.icb.uni-due.de/fileadmin/ICB/research/research_reports/ICB-Report-No46.pdf