Delhaize BeLux Achieves Up to 90% Forecast Accuracy Using SymphonyAI's AI-Driven Replenishment Platform

Ahold Delhaize grocery retailer deploys SymphonyAI across 600 stores and five distribution centers, cutting shrink and improving forecast accuracy by up to 10 percentage points

PALO ALTO, Calif.--(BUSINESS WIRE)--When a grocery retailer operates under a pure B2B affiliate model, it cannot push excess inventory to its store partners — which means forecasting has to be right, or the distribution center absorbs the cost. SymphonyAI, a global leader in Vertical AI, today announced that Delhaize, part of the Ahold Delhaize Group, has deployed SymphonyAI's Demand Forecasting and Replenishment solutions across its 600-store affiliated network and five distribution centers in Belgium, replacing reactive, manually intensive ordering processes with an AI-driven, exception-based workflow.

The Delhaize Le Lion / De Leeuw network has no less than 1113 stores in Belgium and Luxembourg. The store network consists of different formulas: Delhaize, Proxy, Shop&Go and louis delhaize. Customers can also shop online via www.delhaize.be, and either pick up their products at the collect points or have them delivered to their homes. Delhaize offers a wide range of over 20,000 quality products.

SymphonyAI's Demand Forecasting and Replenishment solutions generate daily order proposals at both distribution center and store level, integrating with SAP Retail and accounting for vendor calendars, lead times, truck constraints, promotional pre-orders, and available stock across the network. At distribution center level, weekly forecast accuracy now reaches 80 - 85% for dry and frozen categories and 85 - 90% in fresh, excluding promotional periods. For affiliated stores, forecast accuracy has improved by approximately five percentage points on average and up to 10 percentage points for highly seasonal locations. Across categories, the improvement versus the previous approach reaches up to 10 percentage points depending on rotation and item type. DC shrink has been decreasing across all departments without compromising service levels to affiliate partners, while working capital has improved materially as a result of higher forecast accuracy and reduced safety stock requirements.

"Building a best-in-class supply chain on a pure B2B affiliate model is a different challenge than running a traditional retail operation. You cannot push inventory risk downstream to your partners — forecasting has to be right, or you absorb the cost," said Géraldine Durant, Supply Chain Replenishment and Master Data Director at Delhaize. "We have worked with SymphonyAI for more than 15 years, and the decision to move to their AI-based forecasting models was one we made with confidence. The results across both our distribution network and affiliated stores have validated that decision. We are continuing to improve forecast accuracy each year, and our roadmap with SymphonyAI gives us a clear path to raising the bar further."

The shift to exception-based order review has significantly improved productivity for Delhaize’s replenishment teams, freeing specialists to focus on critical alerts and higher-value activities rather than validating every order proposal individually. Today, approximately 20% of DC order proposals are auto-approved without any user intervention, with Delhaize targeting 50% auto-approval as the vendor scope expands. For orders that do require review, the modification rate stands at around 10% in dry categories and 20% in fresh — a reflection of AI proposal quality rather than manual correction.

At store level, affiliated store managers review only a handful of articles per day via handheld devices, focusing on high orders and near-empty shelf exceptions.

Backed by SymphonyAI's Managed Services team, Delhaize continues to improve forecast accuracy by 1.5 - 2 percentage points each year.

"Delhaize operates one of the more demanding retail supply chain environments we work in: a multi-echelon network, a high-fresh assortment, and a B2B pull model that removes the inventory buffer most retailers rely on," said Manish Choudhary, President of Retail, SymphonyAI. "What they have built with our Forecasting AI platform is a replenishment operation that improves continuously, not just at go-live. That compounding accuracy gain is the commercial case for AI in grocery supply chain, and it is exactly what our platform is designed to deliver."

For retailers looking to extend AI's impact beyond replenishment, SymphonyAI's CINDE platform offers a suite of AI-native retail intelligence capabilities spanning retail media, assortment optimization, and space planning. Where Forecasting AI answers the question of how much to order and when, CINDE addresses what to carry, where to place it, and how to monetize the shelf — giving retailers an end-to-end AI layer across the decisions that drive margin. Delhaize’s forecasting deployment represents the supply chain foundation on which broader retail AI strategies are increasingly being built.

To learn more about SymphonyAI's retail AI platform for grocery and CPG, visit symphonyai.com/retail.

About SymphonyAI

SymphonyAI delivers Vertical AI product platforms that help enterprises solve their most complex, high-value challenges — from stopping financial crime to improving store performance and boosting manufacturing efficiency. Trusted by more than 2,000 enterprise customers worldwide, including 200 of the top financial institutions, the top 25 CPG companies, and many of the world's largest grocers and industrial manufacturers, SymphonyAI provides domain-trained applications and pre-built agents that are ready to work on day one. Learn more at https://www.symphonyai.com/.