Abstract
This paper presents an approach to predict warranty repair claims on automotive units based on joint on-board diagnostic and historic warranty repair data. The problem is framed as binary classification, facilitating the applicability of a variety of machine learning techniques. The approach allows automotive manufacturers to make better use of the operational and failure data collected from the field, allowing for better spend forecast and more targeted vehicle health management interventions and campaigns. The research evaluates the performance of Support Vector Machines, Random Forests and Decision Trees on the data set thus obtained is evaluated and the results are presented, highlighting the importance of hyper-parameter tuning for the problem considered. It is shown that the modelling methods employed demonstrate comparable performance, however the Decision Tree approach seems to perform the most consistently across the various target failure codes considered at this time.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Abdelgayed, T.S., Morsi, W.G., Sidhu, T.S.: Fault detection and classification based on co-training of semisupervised machine learning. IEEE Trans. Ind. Electron. 65(2), 1595–1605 (2018). https://doi.org/10.1109/TIE.2017.2726961
Bergstra, J., Bengio, Y.: Random search for hyperparameter optimization. J. Mach. Learn. Res. 13, 281–305 (2012). https://doi.org/10.1162/153244303322533223
Breiman, L.: Random forests. Mach. Learn. 45(1), 5–32 (2001)
Breiman, L., Friedman, J.H., Olshen, R.A., Stone, C.J.: Classification and Regression Trees, p. 432. Wadsworth International Group, Belmont (1984)
Cawley, G.C., Talbot, N.L.: On over-fitting in model selection and subsequent selection bias in performance evaluation. J. Mach. Learn. Res. 11, 2079–2107 (2010)
Chang, C.C., Lin, C.J.: LIBSVM: a library for support vector machines. ACM Trans. Intell. Syst. Technol. 2, 27:1–27:27 (2011). Software http://www.csie.ntu.edu.tw/~cjlin/libsvm
Chinchor, N.: MUC-4 evaluation metrics. In: Proceedings of the 4th Conference on Message Understanding, pp. 22–29. Association for Computational Linguistics (1992)
Fan, Y., Nowaczyk, S., Rögnvaldsson, T.S.: Incorporating expert knowledge into a self-organized approach for predicting compressor faults in a city bus fleet. In: SCAI, pp. 58–67 (2015)
Horváth, T., Mantovani, R.G., de Carvalho, A.C.: Effects of random sampling on SVM hyper-parameter tuning. In: International Conference on Intelligent Systems Design and Applications, pp. 268–278. Springer (2016)
Luo, B., Wang, H., Liu, H., Li, B., Peng, F.: Early fault detection of machine tools based on deep learning and dynamic identification. IEEE Trans. Ind. Electron. 66(1), 509–518 (2018). https://doi.org/10.1109/TIE.2018.2807414
Mathew, J., Pang, C.K., Luo, M., Leong, W.H.: Classification of imbalanced data by oversampling in kernel space of support vector machines. IEEE Trans. Neural Netw. Learn. Syst. 29(9), 4065–4076 (2018). https://doi.org/10.1109/TNNLS.2017.2751612
Nowaczyk, S., Prytz, R., Rögnvaldsson, T., Byttner, S.: Towards a machine learning algorithm for predicting truck compressor failures using logged vehicle data. Front. Artif. Intell. Appl. 257, 205–214 (2013). https://doi.org/10.3233/978-1-61499-330-8-205
Prytz, R., Nowaczyk, S., Rögnvaldsson, T., Byttner, S.: Predicting the need for vehicle compressor repairs using maintenance records and logged vehicle data. Eng. Appl. Artif. Intell. 41, 139–150 (2015). https://doi.org/10.1016/j.engappai.2015.02.009
Rögnvaldsson, T., Nowaczyk, S., Byttner, S., Prytz, R., Svensson, M.: Self-monitoring for maintenance of vehicle fleets (2018). https://doi.org/10.1007/s10618-017-0538-6
Shafi, U., Safi, A., Shahid, A.R., Ziauddin, S., Saleem, M.Q.: Vehicle remote health monitoring and prognostic maintenance system. J. Adv. Transp. 2018 (2018). https://doi.org/10.1155/2018/8061514
Acknowledgments
The research presented in this paper is funded by the Intelligent Personalised Powertrain Health Care research project, in collaboration with Jaguar Land Rover. The authors would like to thank the anonymous reviewers for their valuable feedback.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Torgunov, D., Trundle, P., Campean, F., Neagu, D., Sherratt, A. (2020). Vehicle Warranty Claim Prediction from Diagnostic Data Using Classification. In: Ju, Z., Yang, L., Yang, C., Gegov, A., Zhou, D. (eds) Advances in Computational Intelligence Systems. UKCI 2019. Advances in Intelligent Systems and Computing, vol 1043. Springer, Cham. https://doi.org/10.1007/978-3-030-29933-0_40
Download citation
DOI: https://doi.org/10.1007/978-3-030-29933-0_40
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-29932-3
Online ISBN: 978-3-030-29933-0
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)