Solving an Intractable Stochastic Partial Backordering Inventory Problem Using Machine Learning
This paper addresses the intractability of order crossover in a partial backordering inventory problem. Here, the Artificial Neural Network (ANN), which is a machine leaning algorithm is used to solve a stochastic inventory problem. The results for examining order crossover with the back-propagation ANN shows notable reduction in inventory cost in comparison to linear regression method. A numerical study is taken to demonstrate the findings. This paper further draws insight on effectiveness of machine learning in comparison to regression.
KeywordsANN Order crossover Machine learning
- 5.Srivastav, A., Agrawal, S.: On single item time weighted mixture inventory models with independent stochastic lead times. Int. J. Serv. Oper. Manag. 22, 101–121 (2015)Google Scholar
- 6.Srivastav, A., Agrawal, S.: On a single item single stage mixture inventory models with independent stochastic lead times. Oper. Res. Int. J. (2018). https://doi.org/10.1007/s12351-018-0408-z
- 7.Srivastav, A., Agrawal, S.: Multi-objective optimization of mixture inventory system experiencing order crossover. Ann. Oper. Res. (2018). https://doi.org/10.1007/s10479-017-2744-4
- 17.Silver, E.A., Pyke, D.F., Peterson, R.: Inventory Management and Production Planning and Scheduling. Wiley, New York (1998)Google Scholar