Title: A graph-theoretical approach in dynamic decision-making analysis

Authors: Henrik Kallio

Addresses: Department of Information and Service Management, Aalto University School of Business, Finland

Abstract: The world has become complex in nature which means that decision-making happens more in dynamically changing conditions. This sets challenges as well as gives opportunities for research in economics. Big data gathered from decision-making behaviour opens up interesting avenues for studies and need to be investigated comprehensively. This requires development of new methodological approaches which are beneficial in analysing and building relevant theories. This paper presents a novel machine-learning methodology that is based on data mining with graph-theoretical innovation. The usefulness of methodology is demonstrated with data gathered from dynamic business simulation game. Results show that the methodology can reveal new insights from the dynamic decision-making behaviour, for example centrality of decisions has the impact on the success in dynamic environment. The methodology developed in this paper may also be applied for practical purposes, for instance in order to study the usage of digital devices.

Keywords: dynamic decision-making; information systems; business simulations; economics; big data; machine learning; data mining; link mining; graph theory; decision tree analysis.

DOI: 10.1504/IJADS.2026.153504

International Journal of Applied Decision Sciences, 2026 Vol.19 No.3, pp.314 - 340

Received: 03 Jan 2025
Accepted: 07 Apr 2025
Published online: 12 May 2026 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article