Sign up

Boggi Milano automates its supply chain replenishment with Evo Pricing, the Microsoft-powered Artificial Intelligence

Executive summary

Innovation is core to Boggi Milano. The founding value that enabled its transformation from a small boutique in 1939 to the fastest-growing ambassador of premium Italian style for cosmopolitan men all over the world, with 190 stores in 38 countries. The latest example is the company’s recent adoption of fully automated supply chain replenishment, an innovation introduced in partnership with Evo Pricing. This Microsoft-powered Artificial Intelligence solution enabled 4% like-for-like revenue growth, even while overall stock shrank by 12%, thanks to accelerated learning and greater local relevance.

Supply chain is the backbone of fashion retail. And Artificial Intelligence is the next generation of technology to deliver to ever-demanding customers.

– Paolo Selva, CEO Boggi Milano

“I joined Boggi because of its entrepreneurial, innovative energy to drive change — never more needed than in these amazing but challenging times for the fashion industry,” says Luca Crippa, Chief Data Officer at Boggi Milano. “Technology opens up new opportunities that were unthinkable of just five years ago, a powerful ally and the most solid lever to transform our way of delivering quality to our customers. And for our merchandising, we chose Evo Pricing to leverage the best data assets, expertise and academic research thanks to its specialized solutions, built on top of already familiar Microsoft products, like Excel.”

Today’s customers expect a different level of service delivery. “Digital technology,” says Crippa “allows customers to be more connected, with access to more information, anytime, anywhere. So, they expect the same immediacy from our offering, a deep understanding of their personal needs.”

Moving from ‘push’ to ‘pull’

Boggi built its success on providing expert, personal customer relationships. However, traditionally high-end retailers carry excess stock in their stores and warehouses, due to the opportunity cost of missing even just one sale due to lack of inventory. And this led to narrower, and more uniform, product ranges offered than would be desirable otherwise, by dynamically adapting to local demand in any market.

Carrying the wrong stock in the wrong store at the wrong time may be costly, especially for high-margin premium fashion: marking down unsold merchandise hurts the bottom line. Moreover, distributing stock across stores too early may reduce the flexibility to adjust to customer demand throughout the season. Since carefully designed luxury boutiques can only carry a limited amount of merchandise, poor-selling items take valuable space away from other options with higher potential.

“We had developed our supply chain systems in-house, over the course of the previous 20 years,” says Marco Benasedo, Chief Information Officer at Boggi. “While the technology was robust, it was designed for a smaller retail footprint, mostly in Italy. Our accelerated international growth suggested we rethink this system, to allow for greater local customization, faster reaction to changes in demand and efficient rebalancing of availability through point-to-point exchange of inventory across stores.”

Benasedo adds: “We searched for a leading-edge partner with specific focus and skills in predictive analytics, which we found with Evo Pricing, also thanks to their partnership with Microsoft Azure.”

Innovating the supply chain

The automated demand forecast of Evo Pricing allocates the right products to the right stores at the right time, reducing wasted overstock and freeing up faster-selling inventory while reducing complexity in the supply chain.

“If you ask a fashion manager what they are most concerned about, it’s the ability to meet and anticipate customer demand, while responding to trends and keeping day-to-day operations manageable — it’s a lot about innovation that works,” says Elena Marocco, chief supply chain solution architect at Evo Pricing. “Building on the Microsoft stack with Azure, SQL Server and Excel, we deliver cutting-edge solutions to fulfill precisely those needs.”

We create value from decision automation. Specifically, our Supply Chain solution is now able to forecast demand for nearly any type of product and service, leveraging proprietary data on 1.2 billion people globally and $100 billion of B2C & B2B transactions: we invested over 200 cumulative person-years of Research & Development over the past 6 years to achieve this milestone.

– Fabrizio Fantini, CEO Evo Pricing

Evo Pricing predicts daily sales for each store right down to product and size, showing how such accurate store-level demand forecast leads to greater diversification of product range and stock levels among stores, products, and customer segments relative to the past, in turn unlocking greater inventory efficiency. The transformative impact of its solutions has been featured in a Harvard Business School case study in 2019.

Essentially, their strategy is to sell more with less inventory overall, thanks to the intuition that at a granular level, each store only needs very specific products and sizes every day, based on its local, seasonal demand.

Increasing efficiency

Reducing stock apparently should automatically increase the efficiency of inventory allocation, but in reality, lower stock allocation magnifies the impact of errors in the demand forecast. However, using Microsoft-powered AI to do the heavy lifting, a 72% average reduction in forecast errors led to significant real-time improvement in customer service levels and reduction in stock-outs.

Evo Pricing first integrated the company’s product, store, and customer attributes into its system by matching the company’s internal data to its proprietary data model: market benchmarks, industry statistics, social trends and customer profiles — even the local weather.

Armed with a more accurate customer demand forecast, overloading each store with stock early in the season was no longer unnecessary. “While it is impossible to anticipate customer needs before they emerge, we can increase customer relevance by delivering the right products to the right stores at the right moment – crucially also by exchanging inventory across stores when economically profitable,” says Fabrizio Fantini of Evo Pricing.

The replenishment solution mapped out stock transfers to exchange higher-demand articles across the right stores in the right sizes, so that items not selling well in one location could be transferred to another store, transforming dead inventory risking to be wasted into profitable sales.

A more impactful and accurate supply chain system delivers positive ROI quickly.

Within the initial seven-week A/B test, the new automated replenishment system increased like-for-like sales by 4% while reducing inventory levels by 12%.

– Alessandro Pozzi, Chief Operations Officer Boggi Milano

In particular for inventory transfers across stores, Pozzi saw “a whole order of magnitude improvement in the sell-through of products after they were transferred to a different store, compared to before: this reinforced our confidence in the predictive abilities of this innovative application of Artificial Intelligence, beyond any reasonable doubt.”

For Boggi Milano, less really ended up being more. Within just seven weeks, the Microsoft-powered solution of Evo Pricing simplified inventory management, reduced overstock and fragmentation, and eased warehousing and storage issues — all while increasing full-price sell-through and revenues.

About the author

Fabrizio Fantini is the brain behind Evo. His 2009 PhD in Applied Mathematics, proving how simple algorithms can outperform even the most expensive commercial airline pricing software, is the basis for the core scientific research behind our solutions. He holds an MBA from Harvard Business School and has previously worked for 10 years at McKinsey & Company.

He is thrilled to help clients create value and loves creating powerful but simple to use solutions. His ideal software has no user manual but enables users to stand on the shoulders of giants.

Hey! Was this page helpful?

We’re always looking to make our docs better, please let us know if you have any
suggestions or advice about what’s working and what’s not!

Send Feedback