CARREFOUR Google Data Lab: Using AI to drive value in store based on the AI Factory’s operating model of Artefact

AI offers incredible opportunities in the retail space. Global retailer Carrefour is going through a digital transformation and has partnered with Google and Artefact to leverage the power of AI and capture value in several departments: assortment, pricing, supply chain, store operations, ecommerce, and marketing.

Carrefour’s ambition is to sift through its vast trove of data (4 billions annual transactions, 1 million daily visits to digital platforms) to identify unaddressed issues, define use cases, scale AI solutions, spread the adoption of AI within the company and conduct training and upskilling.

Carrefour chose to set up a multidisciplinary hub of internal and external data experts.

Artefact devised an operating model through an agile methodology composed of several steps: Structure, Discovery, Minimum Viable Model (MVM), Prototype, Scale and Optimization.

Carrefour selected a dedicated AI lead and worked with its partners Google and Artefact to establish guidelines. Artefact also assembled Feature Teams, each working on a single unique key performance indicator. They are made of a business owner, an AI product owner, a data engineer and a data scientist.

Use cases were developed in several departments, such as assortment optimization, dynamic pricing,  relevant promotions,  sales prediction, inventory management, out of stock prevention, fraud optimization, customization of marketing, churn reduction, and algorithm product recommendation.

Relying on a gradual approach to gain speed and scale while enabling innovation is key to turn experimentation into innovation.

Artefact’s initial experiments proved successful and are being scaled through the organization and deployed across different product categories, store formats, and countries.

Carrefour developed an assortment recommendation tool that helped the chain support a more personalized selection at the store level, giving store directors the autonomy to influence inventory needs.

Some stores saw up to 40% additional revenue on some single items.

The models made to optimize operations with precision across the supply chain were able to detect stockouts in just an hour when it used to take two days and to accurately predict the volume of curb pickup sales down to the half-hour and allow store managers to staff their operations teams accordingly.

AI factories are a combination of talented individuals, methods, and technologies in the service of brands looking for scalable operational efficiencies and business successes.