How Versace Transformed In-Season Inventory Management with Intelo’s AI Agents

Background

Versace, a globally recognized luxury fashion house, faced increasing complexity in managing in-season inventory across its retail network. Frequent out-of-stock situations on top-selling styles, uncertainty in forecasting new products, and the inability to distinguish between true demand shortfalls and missed sales made planning cycles inefficient and reactive.

The brand needed a more dynamic, data-driven approach to decision-making across allocation, replenishment, and consolidation processes.

Challenges

1. Out-of-Stock Losses:
Fast-selling styles frequently went out of stock before replenishment could be initiated, resulting in missed revenue opportunities.

2. Forecasting Newness:
Buyers often had to rely on gut feel when planning for new styles. Without a reliable early demand signal, this led to overbuying certain items and underbuying others.

3. Missed Sales vs. Weak Demand:
It was difficult to isolate whether poor performance was due to low consumer demand or simply stock-outs, which made recalibrating future buys and allocations unreliable.

Solution

Versace partnered with Intelo to implement a set of AI-driven agents purpose-built for in-season agility. These agents addressed core bottlenecks in forecasting, replenishment, and allocation with automated, real-time intelligence.

In-Season Replenishment & Re-Forecasting Agent
This agent continuously monitored live sell-through and automatically flagged looming stock-outs. It enabled timely reorders before shelves emptied, reducing lost sales and improving availability on key styles.

Lost Sales (Missed Opportunity) Agent
By identifying where and when demand exceeded supply, this agent helped distinguish between genuine underperformance and missed sales due to stock-outs. The insights were used to recalibrate baseline demand and improve future forecasts.

Style Similarity & Newness Forecasting Agent
To address the uncertainty around new product introductions, Intelo’s model leveraged historical data from “look-alike” or similar styles. This provided early-stage demand signals for new items, helping planners align buy quantities more closely with expected performance.

Door-Level Allocation & Demand Agent
This agent produced precise, door-specific inventory recommendations by factoring in local sales trends, store capacity, and live performance. It ensured the right styles and sizes were allocated to the right locations without overloading low-performing stores.

Key Results

• 85% faster allocation cycles
  Allocation time was reduced from 7 days to same-day execution.
• 90% faster rebalancing
  Rebalancing turnaround dropped from 11 days to next-morning execution.
• $100K in annual labor savings
  Senior planners were able to shift time from manual allocation to high-value merchandising strategy.
• 6 percentage point increase in sell-through
  Sell-through improved from 67% to 73%, resulting in higher full-price sales and reduced markdown dependency.‍

Conclusion

By implementing Intelo’s in-season intelligence agents, Versace transitioned from reactive planning to a proactive, automated inventory strategy. The partnership not only improved operational speed and reduced planner workload but also delivered measurable business impact—through increased revenue, stronger forecasting accuracy, and smarter allocation across their global retail footprint.