Real-Time Dynamic Pricing Optimization
From use case: Real-Time Dynamic Pricing Optimization
A major Dutch grocery chain operated by Ahold Delhaize has deployed AI-powered dynamic discounting across all stores equipped with electronic shelf labels since late 2022. The system, developed in-house with consulting support from Wasteless, automatically reduces prices on fresh products such as chicken and fish based on sell-by dates, with discounts increasing as expiration approaches, reaching up to 70%. The self-learning algorithm considers historical sales data, local and seasonal characteristics, weather forecasts, and current stock levels to optimize markdown timing and depth. In September 2025, the grocer consolidated four food waste reduction initiatives into a single customer-facing app feature, targeting a 25% increase in marked-down product sales and a goal of saving over five million kilograms of food annually. A related Ahold Delhaize initiative using AI-improved demand forecasting at the company's Belgian subsidiary achieved a 26% improvement in forecast accuracy and a projected 21% reduction in food waste, according to a 2022 Kickstart AI report.
In the United States, a major grocery chain has expanded electronic shelf label technology to approximately 500 stores and partnered with IntelligenceNode in February 2024 to apply AI and machine learning for dynamic pricing and market analytics on its third-party marketplace. The grocer has stated that the technology is designed to identify opportunities to lower prices on perishable, seasonal, or slow-moving items. In the B2B distribution sector, Wilbur-Ellis, an agricultural products distributor, implemented AI-driven real-time pricing across more than 6,000 SKUs and achieved a 2% margin uplift along with enhanced pricing precision, according to a PROS Holdings case study. A 2025 University of California San Diego study found that dynamic pricing via electronic shelf labels reduced food waste by up to 21%, with virtually no evidence of surge pricing behavior before or after label adoption.