Stochastic Multiobjective Optimization Of Currypuff Production In Smes Using Grey Wolf Algorithm With Inflation And Maintenance Cost Integration

Abstract

Small and medium-sized enterprises (SMEs) in the food manufacturing sector often struggle with production inefficiencies due to inflation, rising wages, and maintenance costs. Traditional planning methods used by SMEs are typically manual or static, lacking the ability to respond to real-time economic fluctuations. These limitations lead to poor cost control, suboptimal production levels, and reduced profitability. This study proposes a stochastic multiobjective optimization model using the Grey Wolf Optimization (GWO) algorithm to determine the optimal monthly production of currypuffs over five years. The model integrates key economic variables such as wage inflation, raw material cost escalation, selling price changes, and production growth, all treated as stochastic inputs. Baseline daily production is 160 packs at RM 8.55 per pack. After optimization, production scales to 17,828 packs annually, while cost per pack stabilizes at RM 9.16. Profit margins improve from 14.49% to 21.61%, demonstrating the model’s ability to enhance operational planning under uncertainty. This research offers a practical, data-driven decision-support tool that enables SMEs to optimize production strategies, maintain cost efficiency, and improve financial sustainability in volatile economic environments. Unlike deterministic models, the proposed GWO-based stochastic optimization uniquely incorporates inflation, wage dynamics, and cost escalation offering a practical decision-support tool tailored specifically to SME food production, which is underrepresented in current optimization research.