This is the story of how Hunkemöller’s merchandising team worked together with an AI model, delivered by ADC Data & AI Consulting, to deliver better discounting outcomes and delivering better sell-through at higher margins. 

Joost van Rens, Chief Operating Officer at Hunkemöller, explains what the numbers showed and how the merchandising team changed its ways after adopting artificial intelligence. 

Results of the transformation 

Hunkemöller’s merchandising team carried out the transformation with ADC, guided by a benchmark ADC sets for the retail industry for 3 months: 

• Revenue up 8 percent. 
• Margin up 2 percentage points in three months. 

The pilot ran from mid-November to the end of January—about two and a half months. In that time, Hunkemöller not only reached the benchmark. They passed it. Faster than expected, on both revenue and margin. 

Today, AI-driven markdown runs across every Hunkemöller channel—online and in stores, in every country where they operate. To anchor the change, ten key people were retrained on the new pricing principles.

Hear the Hunkemöller case live. RetailTrends Conference, 13 November. Request a seat 

Why Hunkemöller chose to transform markdown with AI 

A deep review was the trigger. Markdown across the company was increasing and showed persistent negative trends: 

• Full-price sell-through percentage was falling. 
• Average discounts—and the share of high-discount tiers—were rising. 

Hunkemöller operating in many countries and across offline and online channels. The complexity was predicting the right discount for each market and channel was a Herculean task and as a result its average discount sat above historical norms. 

The message was clear: too much was being given away. Stronger demand forecasting was needed to avoid flushing stock with low prices. 

A gut feeling became a structured challenge—one that called for a systematic, AI-driven approach to markdown. 

How markdown worked before AI 

Before the transformation, pricing and markdown were fully manual. The team relied on experience. Decisions came step by step as the sale unfolded. The full season was not planned in one go. Meanwhile, scale—and the need for tighter control—kept growing. Managing at SKU or fine product-group level in Excel alone became too hard. 

So Hunkemöller turned to ADC to implement and test an AI approach to discount management. 

AB Testing to determine the impact of working with AI  

To see whether the new approach brings any benefits to the business in a short period of time, we started with AB testing of SPARO. SPARO — Strategic Pricing and Revenue Optimization. It is a fully customizable decision-support system that blends machine learning with business logic, delivering pricing recommendations in structured “waves” rather than one-off changes. It is designed to balance speed and margin protection—moving stock efficiently without discounting too deeply. 

SPARO was used in the whole sale period—starting with Black Friday and running all the way through End-of-Season sales —running in both channels (online and in stores) across every country. 

To get an objective read, they set up test and control:

• Test: ADC’s discount recommendations plus the merchandising team’s judgment. 
• Control: the traditional approach by the merchandising team alone. 

They did not just compare discount depth. They tracked margin and volume, too—because it is easy to cut deeper and lose units. On all three, the results when also using  + SPARO were much better. 

What changed in the merchandising team’s workflow 

With SPARO, Hunkemöller added a new step to the pricing cadence. 

1. ADC generates recommended discount levels. 
2. The merchandising team reviews them and gives feedback. 
3. Where context requires it, the team applies targeted overwrites; otherwise, recommendations are accepted as-is. 

Early on, reviews sometimes ran long and created friction. Today, the flow is smooth—reviews and overwrites happen on time and without issues. 

Because SPARO has already proven its advantage, control-group checks have been retired. The approach is now standard practice, under a three-year strategic partnership with ADC. 

What has changed in markdown philosophy 

The planning logic shifted. Previously, each sale stage was handled on its own. Now the entire period is optimized as a single plan. The new flow is deliberate: the highest discounts are reserved for a small slice of tail stock—capturing more sales earlier and lifting overall margin. Control is more granular: discounts are tuned to specific items and situations, keeping cuts precise rather than broad. 

Advice from Joost van Rens, COO at Hunkemöller 

AI for markdown works best when there’s scale in assortment and data. You don’t need to be international. Models run per country, with smaller markets grouped where it makes sense. 

What matters is the foundation: 

• two or more years of clean transaction, price, and inventory history, 
• hundreds of products per season or category, 
• enough price variation to estimate elasticity, 
• clear stock signals and channel flags (online / stores). 

Adoption is typically easier in e-commerce—no shelf labels to reprint—so levels can be very precise. In stores, tiered levels keep the offer clear for shoppers. 

This is not about replacing people. It is about a stronger partnership: The merchandising team with SPARO. ADC introduced their model to us. We added Hunkemöller’s constraints and business rules, tested it, saw the uplift, and adopted it as our standard. 

If you are considering it, start with a fit check with ADC: a quick data diagnostic and back-test to confirm signal strength—then a focused pilot in a sale period. 

Insights from Jessica Wilson, Head of Merchandising, and Samantha Swain, Chief Merchandise Officer 

Our collaboration with ADC was successful. We established a good relationship quickly and worked together well to deliver results. The use for End of Season Sale was productive.  

Once the model learned our parameters, it helped a lot. It pushed us to go deeper on the right items and move faster. It also removed a lot of admin, so we could focus on analysis. 

Event driven promotions like Black Friday are more challenging because they limit the models freedom. This was due to internal limitations / complexities regarding retail layouts and workload. It therefore required greater collaboration to achieve results. 

This is a good tool. If we were challenged on where we think the solution works best, I would say pure e-commerce, simply because the tool then has less constraints and can work all year round.  But we find it a great support on true clearance activity.  

See Hunkemöller and ADC on stage at the RetailTrends Conference on 13 November

Full AI markdown case with live Q&A. Invitation only. Apply for a pass.