Large-Scale Inventory Optimization: A Recurrent Neural Networks-Inspired Simulation Approach

Many large-scale production networks include thousands of types of final products and tens to hundreds of thousands of types of raw materials and intermediate products. These networks face complicated inventory management decisions, which are often too complicated for inventory models and too large for simulation models. In this paper, by combining efficient computational tools of recurrent neural networks (RNNs) and the structural information of production networks, we propose an RNN-inspired simulation approach that may be thousands of times faster than the existing simulation approach and is capable of solving large-scale inventory optimization problems in a reasonable amount of time.

Automated summary

This paper proposes an RNN-inspired simulation approach that combines computational tools of recurrent neural networks (RNNs) and the structural information of production networks. It can solve large-scale inventory optimization problems thousands of times faster than the existing simulation approach.