Application of data-mining techniques to predict and rank maritime non-conformities in tanker shipping companies using accident inspection reports


Navas de Maya B., Arslan Ö., Akyüz E., Kurt R. E., Turan O.

SHIPS AND OFFSHORE STRUCTURES, vol.17, no.3, pp.687-694, 2022 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 17 Issue: 3
  • Publication Date: 2022
  • Doi Number: 10.1080/17445302.2020.1862530
  • Journal Name: SHIPS AND OFFSHORE STRUCTURES
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Applied Science & Technology Source, Aquatic Science & Fisheries Abstracts (ASFA), Compendex, Computer & Applied Sciences, INSPEC
  • Page Numbers: pp.687-694
  • Keywords: data mining techniques, maritime inspections, Maritime safety, non-conformities, WEKA
  • Istanbul Technical University Affiliated: Yes

Abstract

The application of data mining techniques is an extended practice in numerous domains; however, within the context of maritime inspections, the aforementioned methods are rarely applied. Thus, the application of data-mining techniques for the prediction and ranking of non-conformities identified during vessel inspections could be of significant managerial contribution to the safety of shipping companies, as non-conformities could potentially lead to real accidents if not addressed adequately. Hence, specific data mining methods are investigated and applied in this paper to predict and rank non-conformities on oil tankers using a database recorded by tanker shipping companies in Turkey from 2006 to 2019. The results of this study reveal that specific non-conformities, for instance, inadequate ice operations or inadequate general appearance and condition of hull, superstructure and external weather decks, are not company-based problems, rather they are industry wide issues for all tanker shipping companies.