Izvorni znanstveni članak

Application of Artificial Neural Networks to Multiple Criteria Inventory Classification

Katica ŠIMUNOVIĆ ; Strojarski fakultet u Slavonskom Brodu Sveučilišta J. J. Strossmayera u Osijeku,Slavonski Brod, Hrvatska
Goran ŠIMUNOVIĆ ; Strojarski fakultet u Slavonskom Brodu Sveučilišta J. J. Strossmayera u Osijeku,Slavonski Brod, Hrvatska
Tomislav ŠARIĆ ; Strojarski fakultet u Slavonskom Brodu Sveučilišta J. J. Strossmayera u Osijeku,Slavonski Brod, Hrvatska

Sažetak

Inventory classification is a very important part of inventory control which represents the technique of operational research discipline. A systematicapproach to the inventory control and classification may have a significant influence on company competitiveness. The paper describes the results obtained by investigating the application of neural networks in multiple criteria inventory classification. Various structures of a back-propagation neural network have been analysed and the optimal one with the minimum Root Mean Square error selected. The predicted results are compared to those obtained by the multiple criteria classification using the analytical hierarchy process.

Ključne riječi

Analytical hierarchy process; Artificial intelligence; Multiple criteria inventory classification; Neural network

Hrčak ID:

48243

URI

https://hrcak.srce.hr/48243

Datum izdavanja:

31.8.2009.

Posjeta: 1.895 *