Warranty optimisation based on the prediction of costs to the manufacturer using neural network model and Monte Carlo simulation
Abstract
Warranty is a powerful marketing tool, but it always involves additional costs to the manufacturer. In order to reduce these costs and make use of warranty's marketing potential, the manufacturer needs to master the techniques for warranty cost prediction according to the reliability characteristics of the product. In this paper a combination free replacement and pro rata warranty policy is analysed as warranty model for one type of light bulbs. Since operating conditions have a great impact on product reliability, they need to be considered in such analysis. A neural network model is used to predict light bulb reliability characteristics based on the data from the tests of light bulbs in various operating conditions. Compared with a linear regression model used in the literature for similar tasks, the neural network model proved to be a more accurate method for such prediction. Reliability parameters obtained in this way are later used in Monte Carlo simulation for the prediction of t...imes to failure needed for warranty cost calculation. The results of the analysis make possible for the manufacturer to choose the optimal warranty policy based on expected product operating conditions. In such a way, the manufacturer can lower the costs and increase the profit.
Keywords:
warranty costs / neural network / Monte Carlo simulation / combination warrantySource:
International Journal of Systems Science, 2015, 46, 3, 535-545Publisher:
- Taylor & Francis Ltd, Abingdon
Funding / projects:
- Scientific-technological support to enhancing the safety of special road and rail vehicles (RS-MESTD-Technological Development (TD or TR)-35045)
- Developed new methods for diagnosis and examination mechanical structures (RS-MESTD-Technological Development (TD or TR)-35040)
DOI: 10.1080/00207721.2013.792972
ISSN: 0020-7721
WoS: 000343303700014
Scopus: 2-s2.0-84908181089
Collections
Institution/Community
Mašinski fakultetTY - JOUR AU - Stamenković, Dragan AU - Popović, Vladimir PY - 2015 UR - https://machinery.mas.bg.ac.rs/handle/123456789/2193 AB - Warranty is a powerful marketing tool, but it always involves additional costs to the manufacturer. In order to reduce these costs and make use of warranty's marketing potential, the manufacturer needs to master the techniques for warranty cost prediction according to the reliability characteristics of the product. In this paper a combination free replacement and pro rata warranty policy is analysed as warranty model for one type of light bulbs. Since operating conditions have a great impact on product reliability, they need to be considered in such analysis. A neural network model is used to predict light bulb reliability characteristics based on the data from the tests of light bulbs in various operating conditions. Compared with a linear regression model used in the literature for similar tasks, the neural network model proved to be a more accurate method for such prediction. Reliability parameters obtained in this way are later used in Monte Carlo simulation for the prediction of times to failure needed for warranty cost calculation. The results of the analysis make possible for the manufacturer to choose the optimal warranty policy based on expected product operating conditions. In such a way, the manufacturer can lower the costs and increase the profit. PB - Taylor & Francis Ltd, Abingdon T2 - International Journal of Systems Science T1 - Warranty optimisation based on the prediction of costs to the manufacturer using neural network model and Monte Carlo simulation EP - 545 IS - 3 SP - 535 VL - 46 DO - 10.1080/00207721.2013.792972 ER -
@article{ author = "Stamenković, Dragan and Popović, Vladimir", year = "2015", abstract = "Warranty is a powerful marketing tool, but it always involves additional costs to the manufacturer. In order to reduce these costs and make use of warranty's marketing potential, the manufacturer needs to master the techniques for warranty cost prediction according to the reliability characteristics of the product. In this paper a combination free replacement and pro rata warranty policy is analysed as warranty model for one type of light bulbs. Since operating conditions have a great impact on product reliability, they need to be considered in such analysis. A neural network model is used to predict light bulb reliability characteristics based on the data from the tests of light bulbs in various operating conditions. Compared with a linear regression model used in the literature for similar tasks, the neural network model proved to be a more accurate method for such prediction. Reliability parameters obtained in this way are later used in Monte Carlo simulation for the prediction of times to failure needed for warranty cost calculation. The results of the analysis make possible for the manufacturer to choose the optimal warranty policy based on expected product operating conditions. In such a way, the manufacturer can lower the costs and increase the profit.", publisher = "Taylor & Francis Ltd, Abingdon", journal = "International Journal of Systems Science", title = "Warranty optimisation based on the prediction of costs to the manufacturer using neural network model and Monte Carlo simulation", pages = "545-535", number = "3", volume = "46", doi = "10.1080/00207721.2013.792972" }
Stamenković, D.,& Popović, V.. (2015). Warranty optimisation based on the prediction of costs to the manufacturer using neural network model and Monte Carlo simulation. in International Journal of Systems Science Taylor & Francis Ltd, Abingdon., 46(3), 535-545. https://doi.org/10.1080/00207721.2013.792972
Stamenković D, Popović V. Warranty optimisation based on the prediction of costs to the manufacturer using neural network model and Monte Carlo simulation. in International Journal of Systems Science. 2015;46(3):535-545. doi:10.1080/00207721.2013.792972 .
Stamenković, Dragan, Popović, Vladimir, "Warranty optimisation based on the prediction of costs to the manufacturer using neural network model and Monte Carlo simulation" in International Journal of Systems Science, 46, no. 3 (2015):535-545, https://doi.org/10.1080/00207721.2013.792972 . .