Data-Driven Decision Making for Cost Optimization and Menu Engineering in High-Volume Artisan Bakeries

Abstract

The present study investigates the role of data-driven decision making (DDDM) in optimizing costs and enhancing menu engineering effectiveness in high-volume artisan bakeries. Using a quantitative research design, data were collected from five large-scale artisan bakeries over six months, integrating operational, financial, and customer preference metrics. Key variables included ingredient cost, labor cost, overhead cost, sales volume, and profitability indices. Statistical and predictive analyses comprising multiple regression, menu engineering modeling, Random Forest forecasting, and cluster analysis were employed to evaluate cost-performance dynamics and product portfolio efficiency. Results revealed that ingredient and labor costs exerted significant negative impacts on profit margins, while sales volume demonstrated a strong positive effect. The Random Forest model outperformed traditional models, achieving an R² of 0.93, signifying high predictive accuracy for profitability forecasting. Menu engineering classification identified “Stars” as top-performing items, while “Dogs” were low-value products requiring reconsideration. The findings confirm that adopting DDDM enhances operational efficiency, profitability, and strategic menu management, enabling bakeries to balance artisanal quality with data-informed business intelligence.