Genetic Algorithm Model for Stock Management and Control

Abstract

Stock or inventory control and management have continued to face challenges that include inconsistent tracking, labor-intensive warehousing, inaccurate data, daunting manual documentation, and supply chain complexity. Research-based attempts to solve these challenges have continued to suffer one limitation or another. A genetic algorithm model for inventory control and management that addresses some of the limitations is presented in this paper. The model analyzes numerous orders whose chromosome generation and confirmation require previous order sets and takes the stock levels for the existing delivering sequence for the various products. The notable result of the implementation of the model is its attainment of a seamless, time-proven, high-accuracy, complex-computation-free, and cost-friendly platform for a reliable, functional, and result-oriented inventory system. It also established the relevance of genetic algorithms for achieving an on-demand and cognitive assessment of genetic variables against the selective and variable-compliant approach of the existing systems.