A Comparative Evalution on the Prediction Performance of Regression Algorithms in Machine Learning for Die Design Cost Estimation

Abstract

Abstract: In the automotive industry, accurate estimation of mold costs is of great importance for businesses to maintain a competitive advantage and effectively manage costs. Traditional methods of predicting mold costs are time-consuming and prone to errors. Therefore, machine learning techniques, particularly regression algorithms, offer an innovative approach to mold cost estimation. This study aims to comparatively evaluate the performance of machine learning regression algorithms used in predicting mold costs in the automotive industry. Different types of regression algorithms, including Linear, Ridge, Lasso, K-Nearest Neighbors (KNN), Decision Tree, Random Forest, Support Vector Machine (SVM), Extreme Gradient Boosting, and Light Gradient Boosting Machines, were considered, and their performances on predicting mold costs and error rates were compared. The Random Forest Regression yielded the highest prediction accuracy at 98.197%.

Keywords

• Machine Learning
• Regression
• Automotive
• Die Design Cost

References

1. [1] Naranje, V., Kumar, S., & Hussein, H. M. A. (2014). A knowledge based system for cost estimation of deep drawn parts. Procedia Engineering, 97, 2313-2322.
2. [2] Ning, F., Shi, Y., Cai, M., Xu, W., & Zhang, X. (2020). Manufacturing cost estimation based on a deep-learning method. Journal of Manufacturing Systems, 54, 186-195.
3. [3] Viharos, Zs. J., & Mikó, B., (2011). Artificial neural network approach for injection mould cost estimation. Proceedings of the 44th CIRP Conference on Manufacturing Systems, New Worlds of Manufacturing, Madison, WI, USA (Vol. 13).
4. [4] Florjanič, B., & Kuzman, K., (2012). Estimation of Time for Manufacturing of Injection Moulds Using Artificial Neural Networks-based Model, Preliminary Communication. Polimeri: časopis za plastiku i gumu, 33(1), 12-21.
5. [5] Rodrigues, A., Silva, F. J., Sousa, V. F., Pinto, A. G., Ferreira, L. P., & Pereira, T. (2022). Using an Artificial Neural Network Approach to Predict Machining Time. Metals, 12(10), 1709. [6] Cather, H. L., & Chan, K. H., (2014). Integrated Approach to Computer Aided Estimating. Fourth International Conference on Factory 2000-Advanced Factory Automation (pp. 349-355). IET.
6. [7] Campi, F., Mandolini, M., Favi, C., Checcacci, E., & Germani, M. (2020). An analytical cost estimation model for the design of axisymmetric components with open-die forging technology. The International Journal of Advanced Manufacturing Technology, 110, 1869-1892.
7. [8] SAP, (2023). What is Machine Learning?, Accessed: May. 21,2023, https://www.sap.com/hk/products/artificial-intelligence/what-is-machine-learning.html
8. [9] IBM, (s.a.). What is linear regression?, Accessed: May. 19,2023, https://www.ibm.com/topics/linear-regression

9. [10] Wikipedia, (s.a.). Ridge regression, Accessed: May. 19, 2023, https://en.wikipedia.org/wiki/Ridge_regression
10. [11] Greet Learning Team, (2023). What is lasso regression?,Accessed: May. 19,2023, https://www.mygreatlearning.com/blog/understanding-of-lasso-regression/
11. [12] Bramer, M. A. (2017). Principles of data mining, Springer, London.
12. [13] Maimon, O., & Rokach, L. (2010). Introduction to knowledge discovery and data mining. In Data mining and knowledge discovery handbook (pp. 1-15). Boston, MA: Springer Us.
13. [14] García-Laencina, P. J., Sancho-Gómez, J. L., Figueiras-Vidal, A. R. (2010). Pattern Classification with Missing Data: A Review, Neural Computing and Applications, 19(2), 263-282.
14. [15] Birant, D. (2011). Comparison of Decision Tree Algorithms for Predicting Potential Air Pollutant Emissions with Data Mining Models, Journal of Environmental Informatics, 17(1), 46-53.
15. [16] Ayyadevara, V. K. (2018). Random Forest. In: Pro Machine Learning Algorithms, Springer, 105–116. https://doi.org/10.1007/978-1-4842-3564-5_5
16. [17] Wang, P. W., Lin, C. J. (2014). Support vector machines. In Data Classification: Algorithms and Applications, 187–204. https://doi.org/10.1201/b17320
17. [18] Muratlar, E. R., (2020). XGBoost nasıl çalışır? Neden iyi performans gösterir?, Accessed: Feb. 5,2023, https://www.veribilimiokulu.com/xgboost-nasil-calisir/
18. [19] Khandelval P., (2017). Which algorithm takes the crown: Light GBM vs XGBoost?, Accessed: Feb. 5,2023, https://www.analyticsvidhya.com/blog/2017/06/whichalgorithm-takes-the-crown-light-gbm-vs-xgboost/
19. [20] İnaç, H.; Ayözen, Y.E.; Atalan, A.; Dönmez, C.Ç. (2022). Estimation of Postal Service Delivery Time and Energy Cost with E-Scooter by Machine Learning Algorithms. Appl. Sci., 12, 12266.
20. [21] Atalan, A., Şahin, H., & Atalan, Y. A. (2022). Integration of Machine Learning Algorithms and Discrete-Event Simulation for the Cost of Healthcare Resources. In Healthcare, Vol. 10, No. 10, p. 1920.
21. [22] Eser, G. (2021). Tahmin Problemleri İçin Regresyon Ağacı Ve Komşuluk Tabanlı Yöntemler Geliştirilmesi: Kalıpçılık Sektöründe Bir Uygulama. Bursa Uludağ Üniversitesi Fen Bilimleri Enstitüsü, Yayınlanmamış Yüksek Lisans Tezi, Bursa