Abstract
The distribution of vehicle damages to bodyshops is not cost-effective. Every damage is unique, and every bodyshop has its specialization(s). Currently, the distribution of damages to bodyshops is predominately based on the distance between the customer and the bodyshop. This paper provides a method to optimize the distribution of vehicle damages to bodyshops in a way that the repair is executed by the most cost-effective bodyshop available for a particular damage based on damage and context characteristics. Three machine learning models have been evaluated to determine which is most suitable for predicting the cost of repair for one particular damage for each bodyshop available. The neural network produced the best results with an average error of €383. In order to apply this approach to real-world problems, we highlight the use of data from visual assessment of the damages using computer vision technology and onboard vehicle data in order to yield the biggest improvement in the average prediction error.
References
Bakar, N.M.A., Tahir, I.M.: Applying Multiple Linear Regression and Neural Network to Predict Bank Performance. Int. Bus. Res. 2 (2009). https://doi.org/10.5539/ibr.v2n4p176
Adnan, N., Ahmad, M., Adnan, R.: A comparative study on some methods for handling multicollinearity problems. Matematika 22, 109–119 (2006)
Predicting performance measures using linear regression and neural network: a comparison 1, 84–89 (2013)
Berrar, D.: Cross-Validation (2018). https://doi.org/10.1016/B978-0-12-809633-8.20349-X
Botchkarev, A.: A new typology design of performance metrics to measure errors in machine learning regression algorithms. Interdiscipl. J. Inf. Knowl. Manag. 14, 045–076 (2019). https://doi.org/10.28945/4184
Caruana, R., Lawrence, S., Giles, C.: Overfitting in neural nets: backpropagation, conjugate gradient, and early stopping. Adv. Neural. Inf. Process. Syst. 13, 402–408 (2000)
Chai, T., Draxler, R.R.: Root mean square error (RMSE) or mean absolute error (MAE)?- Arguments against avoiding RMSE in the literature. Geosci. Model Dev. 7(2014), 1247–1250 (2014). https://doi.org/10.5194/gmd-7-1247-2014
ControlExpert. [n.d.]. https://www.controlexpert.com/. Accessed 23 Jun 2021
Daoud, J.I.: Multicollinearity and regression analysis. J. Phys: Conf. Ser. 949, 12009 (2017). https://doi.org/10.1088/1742-6596/949/1/012009
Dave, V., Shah, K.: Comparative analysis of regularization techniques in arteficial neural networks (2019). https://doi.org/10.1729/Journal.22756
Hurwitz, J., Kirsch, D.: Machine Learning for Dummies. Wiley, Hoboken (2018)
Imandoust, S.B., Bolandraftar, M.: Application of K-nearest neighbor (KNN) approach for predicting economic events theoretical background. Int. J. Eng. Res. Appl. 3, 605–610 (2013)
Jahn, M.: Artificial neural network regression models: predicting GDP growth. HWWI Research Papers 185. Hamburg Institute of International Economics (HWWI) (2018)
Jayawardena, S.: Image-Based Automatic Vehicle Damage Detection. Ph.D. Dissertation (2013)
Khamis, A., Ismail, Z., Khalid, H., Mohammed, A.: The effects of outliers data on neural network performance. J. Appl. Sci. 5, 1394–1398 (2005)
Khamis, H.: Measures of association: how to choose? J. Diagnostic Med. Sonography 24(2008), 155–162 (2008). https://doi.org/10.1177/8756479308317006
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization (2017). arXiv:cs.LG/1412.6980
KPMG. Automotive Data Sharing (2020). https://assets.kpmg/content/dam/kpmg/no/pdf/2020/11/Automotive_Data_Sharing_Final%20Report_SVV_KPMG.pdf
McKinsey. Connected car, automotive value chain unbound. Technical Report (2014)
Mirkin, B.: Core Data Analysis: Summarization, Correlation, and Visualization. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-00271-8
Obite, C., Olewuezi, N., Ugwuanyim, G., Bartholomew, D.: Multicollinearity effect in regression analysis: a feed forward artificial neural network approach. Asian J. Probabil. Stat. 22–33 (2020). https://doi.org/10.9734/ajpas/2020/v6i130151
Potdar, K., Pardawala, T., Pai, C.: A comparative study of categorical variable encoding techniques for neural network classifiers. Int. J. Comput. Appl. 175, 7–9 (2017). https://doi.org/10.5120/ijca2017915495
Raschka, S.: Model evaluation, model selection, and algorithm selection in machine learning. CoRR abs/1811.12808 (2018). arXiv: http://arxiv.org/abs/1811.12808
Sharma, S., Sharma, S., Athaiya, A.: Activation functions in neural networks. Int. J. Eng. Appl. Sci. Technol. 4(12), 310–316 (2020)
Snoek, J., Larochelle, H., Adams, R.P.: Practical Bayesian optimization of machine learning algorithms. In: Pereira, F., Burges, C.J.C., Bottou, L., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems, Vol. 25. Curran Associates, Inc. (2012). https://proceedings.neurips.cc/paper/2012/file/05311655a15b75fab86956663e1819cd-Paper.pdf
Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15, 1929–1958 (2014)
Statsmodels.org. Patsy: Contrast Coding Systems for categorical variables (2021). https://www.statsmodels.org/dev/contrasts.html#sum-deviation-coding. Accessed 25 May 2021
Tate, R.: Correlation between a discrete and a continuous variable point-biserial correlation. Ann. Math. Stat. 25(3), 603–607 (1954)
Keras team. Keras Tuner documentation (2021). https://keras-team.github.io/keras-tuner/. Accessed 26 May 2021
van Dijk, M., Harnam, I., Koudijs, D., Botden, M.: Visie door Data - Moving forward in Mobility. Technical Report (2018)
Vermeulen, I.: Gemiddeld schadebedrag boven 1.300 euro-grens (2020). https://automotive-online.nl/management/laatste-nieuws/schade/27000-arbeidsloon-en-hogere-onderdelenkosten-zorgen-voor-stijgend-schadebedrag. Accessed 5 Mar 2021
Willmott, C.J., Matsuura, K.: Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance. Clim. Res. 30, 79–82 (2005). https://doi.org/10.3354/cr030079
Yang, Z., Zhang, A., Sudjianto, A.: Enhancing Explainability of Neural Networks through Architecture Constraints (2019). arXiv:stat.ML/1901.03838
Peys, R.: Noodklok over sterk gestegen kosten schadeherstel (2022). https://www.automobielmanagement.nl/autoschadeherstel/2022/09/12/noodklok-over-sterk-gestegen-kosten-schadeherstel/. Accessed 12 Jan 2024
Gareth Roberts. 40% rise in vehicle repair costs over past five years (2023). https://www.fleetnews.co.uk/news/fleet-industry-news/2023/03/22/40-rise-in-vehicle-repair-costs. Accessed 12 Jan 2014
eurostat. Glossary:Passenger car. https://ec.europa.eu/eurostat/statistics-explained/index.php?title=Glossary:Passenger_car. Accessed 16 Jan 2024
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
der Sluis, F.v., Rivero, C.R., Hooi, J. (2024). Optimized Vehicle Repair Cost by Means of Smart Repair Distribution Model. In: Daimi, K., Al Sadoon, A. (eds) Proceedings of the Second International Conference on Advances in Computing Research (ACR’24). ACR 2024. Lecture Notes in Networks and Systems, vol 956. Springer, Cham. https://doi.org/10.1007/978-3-031-56950-0_15
Download citation
DOI: https://doi.org/10.1007/978-3-031-56950-0_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-56949-4
Online ISBN: 978-3-031-56950-0
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)