From Concept To Plate Data Driven Approaches To Innovative Menu Development In Restaurants

Abstract

The study explores how data analytics can transform traditional menu design into an evidence-based, consumer-centered, and sustainable innovation process. Using a mixed-method analytical framework, data were collected from five full-service restaurants through customer surveys and point-of-sale (POS) systems. Key variables including Consumer Preference Score (CPS), Menu Layout Effectiveness (MLE), Price Elasticity (PE), Sustainability Rating (SR), and Menu Innovation Performance (MIP) were examined through Exploratory Factor Analysis (EFA), Multiple Regression, Cluster Analysis, and Random Forest Modeling. The findings revealed that CPS and MLE exert the strongest positive influence on MIP, while sustainability-related parameters also contribute significantly to innovation success. Cluster analysis identified three restaurant typologies; Consumer-driven innovators, Operational optimizers, and Traditional cost-focused units reflecting varying levels of data maturity and innovation adoption. Predictive analytics further confirmed the high reliability of data-driven forecasting in menu performance assessment (R² = 0.79). Overall, the study concludes that integrating consumer analytics, sustainability metrics, and predictive modeling can optimize menu innovation, enhance customer satisfaction, and promote operational sustainability. The research contributes to both theory and practice by positioning data intelligence as the cornerstone of next-generation culinary innovation.