Supervised Machine Learning in Detecting Patterns in Competitive Actions

L. Valtonen, S. J. Makinen, J. Kirjavainen

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Abstract

This paper explores possibilities to investigate how patterns of competitive actions could be detected with supervised machine learning (SML) methods. Competitive dynamics and the resource-based view are used as theoretical frameworks for classifying competitive actions. These in turn represent the dynamics of industry evolution from competitive actions point of view. We find promising ways to furthering our understanding of detectable patterns in competitive dynamics and industry evolution. Our results show that standard SML methods can be used in pattern recognition but reporting the methods used in detail are of paramount importance in facilitating peer-review and scientific replication and producing credible results.

Original languageEnglish
Title of host publication2021 IEEE International Conference on Industrial Engineering and Engineering Management, IEEM 2021
PublisherIEEE
Pages442-446
Number of pages5
ISBN (Electronic)9781665437714
DOIs
Publication statusPublished - 2021
Publication typeA4 Article in conference proceedings
EventIEEE International Conference on Industrial Engineering and Engineering Management -
Duration: 1 Jan 1900 → …

Conference

ConferenceIEEE International Conference on Industrial Engineering and Engineering Management
Period1/01/00 → …

Keywords

  • Competitive actions
  • Competitive dynamics
  • Supervised machine learning

Publication forum classification

  • Publication forum level 0

ASJC Scopus subject areas

  • Strategy and Management
  • Artificial Intelligence
  • Computer Science Applications
  • Information Systems and Management
  • Industrial and Manufacturing Engineering
  • Control and Optimization

Fingerprint

Dive into the research topics of 'Supervised Machine Learning in Detecting Patterns in Competitive Actions'. Together they form a unique fingerprint.

Cite this