Sign up

Boggi – Case Study

Boggi Milano was expanding internationally, and its in-house supply chain system could no longer manage inventory efficiently at scale. Could a new system accelerate adaptation to local demand?

Boggi implemented a responsive supply chain solution, differentiating inventory by store and size every day using the Evo Transfer tool.

The result: more sales with less inventory in just 7 weeks. Increased inventory efficiency reduced stockouts, and dynamic transfers transformed dead inventory into profitable sales.

Responsive supply chain: +18.2% inventory efficiency
and more sales with less stock

Boggi Milano Case Study





Stock in


Context: about Boggi

Boggi Milano is a luxury men’s fashion brand with 190 stores in 38 countries. In recent years, Boggi has transformed from a respected national brand to a rapidly growing ambassador of cosmopolitan Italian style for men worldwide.

Innovation is critical to Boggi’s success. It’s the value that empowered them to expand from a single boutique to a leader in the men’s fashion world. It’s also what motivated them to develop in-house supply chain systems over 20 years ago when the technology was still emerging.

As Boggi has expanded internationally however, the in-house system could no longer sustain growth. It was designed for a smaller retail footprint and each new store increased the strain on the system.

The challenge: unpredictable customer response to variable pricing

Alessandro Pozzi, COO of Boggi Milano, didn’t just want to replace the old supply chain system with a more scalable option. He was looking for a solution that would revolutionize inventory efficiency.

We have grown substantially over the past few years, so some growing pains are natural. When you add a new store, it’s not just replenishment logistics that need to be adjusted. You also need to understand the particularities of local demand to ship and stock the right products and sizes.

I wanted to find an innovative system that would accelerate adaptation to local demand, so we would have fewer stockouts and less unsold inventory.

-Alessandro Pozzi, Boggi COO

Additional critical problems stood in his way:

  1. Limited space for slow-selling items: Even though Boggi now has a presence worldwide, each store is designed to feel like an intimate boutique with a curated collection. There simply isn’t the space to offer and store products that won’t sell in that location.
  2. Logistics costs: A more dynamic inventory system would likely incur higher logistics costs. Pozzi wasn’t willing to invest in cross-store transfers unless the ROI was substantial.
  3. Internal buy-in: Merchandising had previously made all allocation decisions for new stores. It wasn’t clear that they would be willing to trust a system to automate some of these manual tasks.

The solution: responsive supply chain, differentiating by store and size every day

Boggi partnered with Evo to implement Evo Transfer as an innovative supply chain solution. Prescriptive Artificial Intelligence made recommendations based on granular local conditions, allowing for a better understanding of local demand, even in new store locations.

As Boggi expands into unfamiliar markets, we need insights into the unique customer needs in those locations. Guessing has a high failure rate that can lead to dead inventory and waste.

Partnering with Evo gave us access to troves of data on local consumer behaviour and a cutting-edge AI that can analyse this data in combination with our internal data to get the right products in the right sizes at the right location at the right time.

Evo implemented a responsive supply chain strategy: allocating inventory according to real-time local demand on a by-store and by-size basis.

This approach relied on:

1. Tracking historical sales and market data

Evo monitors both internal sales data and the sales data on 177K competitor products, as well as the consumer behaviour of 22% of the EU population.

2. Calculating local demand

Evo Transfer analyzes the data to forecast customer needs over the next week. A more accurate store-level demand forecast leads to greater diversification of product range and stock levels among stores, products and customer segments than before.

3. Allocating the right products in the right sizes to each store

The system accelerates inventory swaps across stores and from the warehouses to ensure each location had the right mix of products to meet demand with the minimum inventory levels possible.

To measure impact, Evo Pricing was initially deployed in a rigorous seven-week A/B pilot test.

We wanted to improve inventory efficiency, but not at the cost of sales. We needed to see that the system could reduce inventory without increasing stockouts.

Pilot impact: +18.2% inventory efficiency

Within the initial 7-week A/B test, the new automated replenishment system increased like-for-like sales by +4% while reducing inventory levels by -12%. Overall, Evo Transfer increased inventory efficiency by +18.2%.

It was amazing how fast the AI created an impact on our bottom line. Even with a significant drop in the amount of inventory held at each store, sales and revenues trended upwards.

Most importantly, the efficiency was pinpointed in areas of greatest impact. The Evo system 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. Dead inventory was transformed into profitable sales.

We 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.

Long-term results: -72% reduction in forecast errors

After the successful pilot, Pozzi expanded the scope and coverage of Evo Transfer. Implementation went smoothly thanks to simple front-ends customized for both the head office and field teams. Impact continued to grow.

While many assume that reducing stock should increase the efficiency of inventory allocation, in reality, lower stock magnifies the impact of errors in the demand forecast. Thanks to its Prescriptive AI, however, Evo reduced forecast errors by +72%, leading to a significant real-time improvement in customer service levels and a reduction in stockouts.

Evo has transformed our approach to replenishment.

Alessandro Pozzi

With the Evo Transfer tool, less really does mean more.

Want to learn more?

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