Skip to main content

Prediction of Container Damage Insurance Claims for Optimized Maritime Port Operations

Part of the Lecture Notes in Computer Science book series (LNAI,volume 10832)

Abstract

A company operating in a commercial maritime port often experiences clients filing insurance claims on damaged shipping containers. In this work, multiple classifiers have been trained on synthesized data, to predict such insurance claims. The results show that Random Forests outperform other classifiers on typical machine learning metrics. Further, insights into the importance of various features in this prediction are discussed, and their deviation from expert opinions. This information facilitates selective information collation to predict container claims, and to rank data sources by relevance. To our knowledge, this is the first publication to investigate the factors associated with container damage and claims, as opposed to ship damage or other related problems.

Keywords

  • Damage Containment
  • Data Source Ranking
  • Container Ships
  • Machine Learning Metrics
  • Relevant Association Rules

These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

This is a preview of subscription content, access via your institution.

Buying options

Chapter
USD   29.95
Price excludes VAT (USA)
  • DOI: 10.1007/978-3-319-89656-4_25
  • Chapter length: 7 pages
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
eBook
USD   64.99
Price excludes VAT (USA)
  • ISBN: 978-3-319-89656-4
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
Softcover Book
USD   84.00
Price excludes VAT (USA)
Fig. 1.
Fig. 2.

Notes

  1. 1.

    The survey (named Bottlenecks in Port Operations) was distributed by a Google Forms link in July 2017, after receiving the necessary approval from the Research Ethics Board of the University of Ottawa.

  2. 2.

    The survey results showed that cargo value, hazardous and/or sensitive cargo were the most important attributes in predicting insurance claims.

References

  1. Bichou, K.: Port Operations, Planning and Logistics. CRC Press, Boca Raton (2014)

    Google Scholar 

  2. Stahlbock, R., Voß, S.: Operations research at container terminals: a literature update. OR Spectr. 30(1), 1–52 (2008)

    MathSciNet  CrossRef  MATH  Google Scholar 

  3. Caponecchia, C., et al.: It won’t happen to me: an investigation of optimism bias in occupational health and safety. J. Appl. Soc. Psychol. 40(3), 601–617 (2010). http://doi.wiley.com/10.1111/j.1559-1816.2010.00589.x/abstract

    CrossRef  Google Scholar 

  4. Yoon, S.-O., et al.: The devil is in the specificity : the negative effect of prediction specificity on prediction accuracy. Psychol. Sci. XX, 1–7 (2010). http://pss.sagepub.com/

    Google Scholar 

  5. Hart, S.G., Staveland, L.E.: Development of NASA-TLX (Task Load Index): results of empirical and theoretical research. http://stavelandhfe.com/images/NASA-TLX_paper.pdf

  6. Tseng, W.-J., et al.: Risk analysis of cargos damages for aquatic products of refrigerated containers: shipping operators’ perspective in Taiwan. Inf. Manag. Bus. Rev. 4(2), 86–94 (2012)

    Google Scholar 

  7. Nir, A.-S., Lin, K., Liang, G.-S.: Port choice behaviour-from the perspective of the shipper. Marit. Policy Manag. 30(2), 165–173 (2003)

    CrossRef  Google Scholar 

  8. Hsu, W.K., Huang, S.S., Yeh, R.J.: An assessment model of safety factors for product tankers in coastal shipping. Saf. Sci. 76, 74–81 (2015)

    CrossRef  Google Scholar 

  9. Hsu, W.-K.K., et al.: Assessing the safety factors of ship berthing operations. J. Navig. 68(03), 576–588 (2015)

    CrossRef  Google Scholar 

  10. France, W.N., et al.: An investigation of head-sea parametric rolling and its influence on container lashing systems. Mar. Technol. 40(1), 1–19 (2003)

    Google Scholar 

  11. Kawahara, Y., Maekawa, K., Ikeda, Y.: A simple prediction formula of roll damping of conventional cargo ships on the basis of Ikeda’s method and its limitation. In: Almeida Santos Neves, M., Belenky, V., de Kat, J., Spyrou, K., Umeda, N. (eds.) Contemporary Ideas on Ship Stability and Capsizing in Waves. Fluid Mechanics and Its Applications, vol. 97, pp. 465–486. Springer, Dordrecht (2011). https://doi.org/10.1007/978-94-007-1482-3_26

    CrossRef  Google Scholar 

  12. Lloyd’s Register (2016). http://www.lr.org/en/

  13. Kelangath, S., et al.: Risk analysis of damaged ships-a data-driven Bayesian approach. Ships Offshore Struct. 7(3), 333–347 (2012)

    CrossRef  Google Scholar 

  14. Stanivuk, T., et al.: How to predict cargo handling times at the sea port affected by weather conditions. Croat. Oper. Res. Rev. 3(1), 103–112 (2012)

    Google Scholar 

  15. Kokotos, D.X., et al.: A classification tree application to predict total ship loss. J. Transp. Stat. 8(2), 31 (2005)

    Google Scholar 

  16. EuroWeather: Douglas Scale (1995). http://www.eurometeo.com/english/read/doc_douglas

  17. NOA Administration: Wave Watch III Model Data (2014)

    Google Scholar 

  18. De Jong, K.: Analysis of the behavior of a class of genetic adaptive systems (1975)

    Google Scholar 

  19. List of Shipping Lines (2017). https://en.wikipedia.org/wiki/List_of_container_shipping_companies_by_ship_fleets_and_containers

  20. Top 100 (2015). www.todaystrucking.com/top100/2015

  21. Pedregosa, F., et al.: Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825–2830 (2011)

    MathSciNet  MATH  Google Scholar 

Download references

Acknowledgments

We would like to thank SciNet on whose infrastructure our experiments were run (Each GPC node runs Intel’s Xeon E5540 8-core CPU at 2.53 GHz, with 16 GB RAM; each P7 node runs an IBM Power 755 server with four 8-core 3.3 GHz Power7 CPUs and 128 GB RAM. Detailed specifications can be found at https://www.scinethpc.ca/). We would also like to thank Montreal Gateway Terminals Partnership and their on-staff domain experts, and professional highway truck driver Alyssa Fred Wai-Yi Wong, for sharing their expertise used in data creation and validation.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Ashwin Panchapakesan .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and Permissions

Copyright information

© 2018 Springer International Publishing AG, part of Springer Nature

About this paper

Verify currency and authenticity via CrossMark

Cite this paper

Panchapakesan, A., Abielmona, R., Falcon, R., Petriu, E. (2018). Prediction of Container Damage Insurance Claims for Optimized Maritime Port Operations. In: Bagheri, E., Cheung, J. (eds) Advances in Artificial Intelligence. Canadian AI 2018. Lecture Notes in Computer Science(), vol 10832. Springer, Cham. https://doi.org/10.1007/978-3-319-89656-4_25

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-89656-4_25

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-89655-7

  • Online ISBN: 978-3-319-89656-4

  • eBook Packages: Computer ScienceComputer Science (R0)