Scaling Personalization Across 12 European Markets: A Decade of E-Commerce Growth with Miinto

Case Study

Scaling Personalization Across 12 European Markets: A Decade of E-Commerce Growth with Miinto

The Results

Martin & Servera validated Retail Media as a scalable revenue stream using Algonomy’s Recommend™ and DSW, without investing in a costly point solution.

From September 2025 through April 2026, the program delivered strong outcomes across all key metrics.

Placements closer to the point of purchase, such as the search results page, consistently delivered the highest engagement and conversion rates.

0 %

Average Purchase Rate

0 %

Revenue attributed to Discover across core Europe

0 X

Incremental revenue from Recommend™ in Sweden

0 +

Markets across Europe

Client Background

Miinto is one of Europe’s largest fashion marketplaces, connecting shoppers with boutiques and brands across 12 markets, from the Nordics to Southern Europe. At that scale, personalization isn’t a feature decision. It’s an infrastructure one.

For almost a decade, Miinto has run Algonomy’s personalization suite across its full market footprint, using Recommend™, Discover, and Engage to cover every meaningful moment in the shopper journey, from product recommendations to discovery and homepage content.

Twelve markets. Three products. One consistent personalization layer.

The Challenge

Different languages, different shopper behaviors, different catalog structures. Most personalization tools break down under that complexity. The usual fix is to customize market by market, which creates inconsistency and makes it hard to improve anything at scale.

Miinto’s approach, built on Algonomy’s personalization suite, takes a different path.

Rather than managing each market separately, Miinto runs a single, unified personalization stack across all twelve. A unified stack across all markets means the same logic, data infrastructure, and optimization levers, regardless of geography. What gets refined in one market strengthens the others. What works in Stockholm gets tested in Warsaw.

The Solution

1 Discover: Turning Exploration Into Revenue

For shoppers who arrive without a specific destination, Discover surfaces personalized product feeds that turn browsing into buying.

Personalized Accessories PLP based on the customer’s affinity towards sunglasses.

Revenue attribution from Discover, the share of total sales traceable to a discovery interaction, reached 33.65% in Belgium and 31.37% in Norway in a single year in 2025.

Across the mid-tier European markets, including Poland, the Netherlands, France, Italy, and Germany, attribution consistently sat between 22% and 27% that same year.

Even in earlier-stage deployments in the UK, Discover accounted for 17.46% of revenue.

The consistency across markets at different stages of maturity is what the almost-decade of optimization delivers. Discovery isn’t a feature that works for Miinto’s best market. It works for all of them.

2 Recommend™: Closing the Loop at the Conversion Moment

Where Discover captures exploratory shoppers, Recommend™ works at the product and cart levels, surfacing relevant suggestions when a shopper is closest to making a purchase.

Relevant product recommendations at PDP, powered by Recommend™.

Revenue attribution from Recommend™ reached 5.76% in Sweden and 5.39% in Norway in 2025, with most European markets contributing in the 3–4% range that same year.

These numbers reflect what a well-tuned recommendation engine should deliver at this stage of the journey: incremental revenue from shoppers already in purchase mode, adding to baskets that are already forming.

Relevant product recommendations at the Add-to-cart page, powered by Recommend™.

Almost a Decade of Compounding

Ongoing optimization is built into how Miinto and Algonomy operate together.

Strategy refinements on recommendation placements, multivariate testing on discovery configurations, and continuous tuning across markets. The partnership is structured around improvement, not maintenance.

Almost a decade of that work shows in the 2025 results. And that’s what the next chapter is built on.

Results

Client background

Challenge

Solution

Get in touch

“We just wanted personalization that actually worked for our customers across every market, without the complexity. Almost a decade with Algonomy has given us the infrastructure, the data, and the partnership to make it real. Today, we have a program that scales across twelve markets, delivers consistent results, and keeps getting stronger.”

Paloma Hellfeier-Truong

Director of Product & CX

Miinto

Your Retail Media program starts here.

Let’s talk

From Pilot to Profit:  How Martin & Servera Built Retail Media In-House

Case Study

From Pilot to Profit:  How Martin & Servera Built Retail Media In-House

Facebook X LinkedIn

The Results

Martin & Servera validated Retail Media as a scalable revenue stream using Algonomy’s Recommend™ and DSW, without investing in a costly point solution.

From September 2025 through April 2026, the program delivered strong outcomes across all key metrics.

Placements closer to the point of purchase, such as the search results page, consistently delivered the highest engagement and conversion rates.

0 %

Average Purchase Rate

0 %

Click-Through Rate (CTR)

0 X

CTR vs. standard recommendations

0 +

Suppliers onboarded within the first year

Client Background

Martin & Servera is Sweden’s leading wholesaler for the restaurant and foodservice industry. Formed in 2012 through the merger of Martin Olsson and Servera R&S, the company supplies fresh produce, beverages, equipment, services, and training to restaurants, cafés, bars, and canteens across the country.

For over a decade, Martin & Servera has partnered with Algonomy, using Recommend™ (with Engage) to deliver personalized, data-driven recommendations on their B2B platform. This helps engage customers, improve relevance, and ensure users quickly find what they need.

Personalized Product Recommendations on Home Page, powered by Recommend™.

The Challenge

Having built a personalized procurement experience, Martin & Servera saw Retail Media as the next growth opportunity. They wanted to monetize website space by displaying sponsored product recommendations from supplier brands and private labels.

While they had identified high-impact placements and built a business case, they lacked the infrastructure to execute. The team needed to:

Automate sponsored placements: Activate sponsored products by keyword, placement, audience, and campaign dates without manual merchandising.
Manage campaigns efficiently: Onboard, monitor, and optimize supplier campaigns without creating operational burden for the eCommerce team.
Personalize sponsored ads: Ensure sponsored products remain relevant through segmentation and behavioral context.
Avoid third-party ad solutions: Validate retail media in-house without revenue share models or vendor lock-in.

Martin & Servera required flexibility, automation, and control without overhead.

The Solution

1 How it works

Martin & Servera activated sponsored recommendations in four key areas:
search results page, search flyout, mini cart, and checkout.

Sponsored product ads for spirits on Search Results page, powered by Recommend™ and DSW.

Suppliers purchase sponsored placements for specific search terms. Martin & Servera manages these agreements and uploads campaign files to DSW. Each file contains the search term, product SKU, campaign dates, and ranking score.

DSW combines campaign inputs with Martin & Servera’s product catalog and customer behavioral data, including searches, clicks, add-to-carts, and purchases collected through Recommend™. Using queries, the data team generated structured tables that mapped keywords to sponsored SKUs.

These tables power custom strategies that automatically inject sponsored products into the right placements for the right audience segments, and activate and expire campaigns, without manual merchandising.

Sponsored product ads for Heinz in the Search Flyout, powered by Recommend™ and DSW.

Built on Martin & Servera’s existing Algonomy setup, the team built a custom campaign planning tool to complement it. Together with Algonomy, this avoided the cost and complexity of a dedicated third-party retail media platform. After go-live, the only ongoing step was regularly uploading supplier campaign files.

Sponsored product ads for milk in the Checkout pop-up, powered by Recommend™ and DSW.

2 What Sets This Program Apart

Built on Existing Personalization Infrastructure
Sponsored product ads are launched on the existing Algonomy stack, with no vendor lock-in or revenue share models. Operationally, this means that Martin & Servera have access to the full suite of merchandising controls within Recommend™, which they use to optimize their campaigns.

With the Segment Library feature, they can create different customer segments based on shopper business type and location, then target those segments in Merchandising Rules to prevent sponsored products from appearing to audiences where they are unlikely to perform well and vice versa.
Full Control with Automation 
Brand relationships, placements, segmentation, and revenue stayed in-house, while execution was automated.
Flexibility by Design
The solution was built with several business goals in mind from the start, making it flexible and versatile enough to serve both supplier brands and private-label products across multiple placements and customer segments.
Built for Growth, Powered by a Small Team
Managed by a small, cross-functional team with high autonomy, the solution is designed to grow with their needs. This makes decision-making agile, without the cost or complexity of a third-party ad server.

What’s Next for Martin & Servera and Algonomy

Martin & Servera is scaling their Retail Media program, closing deals with new suppliers while ensuring existing partners continue to see the value and reinvest. The team is continuing to fine-tune targeting options, gather deeper insights from campaign performance, and build greater automation into their campaign management process.

Results

Client background

Challenge

Solution

Get in touch

Your Retail Media program starts here.

Let’s talk

Wine.com Drives AttributeBased Recommendations for Personalization

Case Study

Wine.com Drives AttributeBased Recommendations for Personalization

Facebook X LinkedIn

Overview

Headquartered in San Francisco, between California’s wine country and Silicon Valley, Wine.com’s mission is to promote the wine lifestyle through innovation—using technology to bring the world of wine to its shoppers’ fingertips.

As the Sr. Director of Product Development, Cam Fortin is tasked with transforming the shopping experience for a million-bottle online wine shop through the most relevant information, tools and expert advice that a wine connoisseur might seek.

Having partnered with Algonomy since 2010, Wine.com was well-versed with how behavioral recommendations could aid consumer research and inform purchases. Many of Wine.com’s behavioral recommendation strategies are product-focused, but a few are attribute-based—a critical differentiator when considering the complex product categories associated with wine.

The Multi-Attribute World of Wine

“Wine is different. People buy the same wine multiple times. Or, if they’re interested in one wine, they’re frequently interested in other wines that are similar, so attribute-based strategies work very well,” says Fortin.

Obvious attributes such as “French,” “red,” and “2010” are easy to deploy in a recommendation strategy such as “People who purchased a French Bordeaux also viewed. But Fortin knew there was a massive opportunity to be leveraged when considering the universe of attributes that applies to wine.

“We’ve always wanted to explore recommending similar products based on the number of attributes they have in common,” he says. Wines may share up to 30 different attributes (big red, smoky, tannic, etc.) in common. Exploring how this subset of common attributes could be exploited for personalization—and capitalized upon—was a compelling challenge. “Being able to run SQL queries and have a ridiculously huge machine to access information from our site directly was something we were very interested in.”

From Concept to Deployment to Production in Hours

Through Algonomy Recommend™, Wine.com was able to test its theory on a custom strategy that leveraged the intersection of multiple attributes. Specifically, Wine.com could access all elements of its customer “map” (browse and purchase history, loyalty, preferences, etc.) and build the algorithm it wished to test, utilizing Algonomy’s Hadoop instance.

Further, Wine.com could measure how its specific algorithm competed against the existing set of pre-built Algonomy algorithms.

The speed with which Fortin moved from concept to deployment to production was unprecedented. “Instead of requesting a change in placement or a tweak in a strategy, we now had the ability to come up with algorithms on our own, create new placements and implement strategies immediately,” says Fortin.

Recommendation strategies are easily managed in the Algonomy Dashboard, which also displays key performance metrics.

Similarity Spells Success

The new “similar products” recommendation strategy—which ranked product recommendations based on the number of attributes they have in common—became one of the best performing strategies in terms of revenue per click, generating about $5 per click.

“We were excited that it worked right off the bat, even though it was just a rough algorithm with little polish to it. Next, we want to weight attributes differently and continue refining this strategy,” says Fortin.

For Fortin, the larger success is related to the ease of use and the speed associated with developing and testing algorithms. The ability for any of his SQL programmers to develop and test several algorithms a month with minimal IT investment was a huge win made possible through Recommend™.

Overview

The Multi-Attribute World of Wine

From Concept to Deployment to Production in Hours

Similarity Spells Success

Get in touch

“The feature is easy to set up and it’s great that it can be tailored to what it is we require, especially when we only want it to show on specific categories!.”

Digital Merchandising Executive

Explore More Resources on Commerce Personalization

See all customer stories

Malaysia Conversational AI

How Cycle & Carriage Singapore turned WhatsApp into its main channel for events, test drives, and high-net-worth engagement

See full story

0 %

Improved lead completion rate

See all customer stories

Looking for a Personalized Demo?

Let’s talk

Cashing in on Bundles – How eCommerce Retailers Can Drive Revenue Growth with Strategic Product Bundles

Case Study

Cashing in on Bundles – How eCommerce Retailers Can Drive Revenue Growth with Strategic Product Bundles

Facebook X LinkedIn

Business Value Delivered

0 %

Click-Through Rate

0 %

Items per Thousand Views

0 %

Revenue per Thousand Views

Overview

Product bundles may not be a novel concept, but they have evolved significantly over time and have proved to be versatile—finding applications across sectors such as fashion, bookstores, tech, beauty, travel, and many more. They present a strategic avenue to increase the number of items a customer adds to their cart, which translates to a higher order value.

When adopting product bundling on your product detail page (PDP), it’s imperative to carefully consider product selection for the bundle, the bundle’s composition, and the steps involved in the implementation process – each a vital contributor to the pursuit of elevated AOV.

Bundle Products: Essential questions include – Which products to bundle? Can the process be fully automated? Do they require compatibility checks? Does it require merchandising? What form of shopper affinity do you aim to drive?
Bundle Composition and Layout: How many products should the bundle include? Should the consumer have the option to customize the bundle? Should the bundle display separate groups with alternatives?
Implementation: Will your in-house developers or third-party integrators develop the bundles on the PDP? Either approach involves backend development to ensure product bundles can be added to the cart, along with front-end development for displaying the bundles in potentially editable, appealing formats.

With Algonomy Recommend™, it’s possible to create and manage comprehensive, effective, and personalized product bundles, simplifying the entire process and ensuring optimized results.

Advanced Algorithms for Product Bundling

Over the years, we have developed algorithms and functionalities that offer customers much more than the conventional ‘Frequently Bought Together’ bundling. Depending on specific business needs, there are several options to choose from for generating optimal product bundles.

Configurable Strategies

Algonomy’s Configurable Strategies allows non-technical users to design their algorithm or strategy by selecting from pre-built models and customization options. This flexibility ensures precise creation of product bundles. This functionality provides the ability to select the AI model to generate the bundle products, apply desired shopper affinity, and adhere to any additional merchandising requirements like restrictions, boosting, etc.

Advanced Merchandising

Algonomy’s Advanced Merchandising utilizes catalog product attributes, enabling merchants to design a personalized shopping experience with their desired level of control. It offers enhanced control over the bundling process for a more tailored outcome.

This includes determining the exact number of products from a certain category, 1WorldSync (formerly CNET) compatibility for the electronics vertical, custom compatibility mapping that enables clients to use their own compatibility mappings to pair compatible products, and creating bundle groups that allow the presentation of alternatives.

Data Science Workbench

Our platform also provides Data Science Workbench, a tool that allows for the creation of custom product recommendation strategies.

For instance, by using the tool, businesses can integrate any external data—such as proprietary complementary data e.g. “complete the look” information or data to rank recommendations on e.g. offline sales—with existing behavioral information and tailor their product bundles just the way they want, based on any shopper affinity.

Bundle Composition, Layout, and Implementation

Algonomy-powered bundles ensure the most relevant bundled products for the shopper by applying personalization. However, keeping the principle of ‘the client is king’ paramount, one can choose for the bundles to be “editable” by providing selected alternatives for groups of products.

Alternatively, consumers can be given the power to “build their own bundle” from the suggested products – the level of customization rests in your control.

Changes or additions to your PDP usually require significant development effort, resources, and time. With the addition of innovative functionalities like Algonomy’s Dynamic Experiences, this burden is lifted. Entire bundles can be designed, created, and added to your site directly from the Algonomy portal, reducing the operational demands on your team.

In summary, Algonomy’s multifaceted solution streamlines the process of creating and managing product bundles, ensuring relevant product recommendations, boosting customer engagement, and ultimately driving sales as the use cases below illustrate.

The Use Case

1 Use Case 1 – Small Change, BIG Impact

Our client, an established player in the bookstore vertical, had been utilizing a basic “Frequently Bought Together” bundle configuration based on a legacy “out of the box” algorithm. Looking to increase their Average Order Value (AOV), they turned their focus on enhancing their bundle setup.

Instead of immediately delving into the complexities of bundle composition and layout, which would necessitate changes in the implementation component, they decided to start out with refining the bundle algorithm.

A new configurable strategy was created focusing on an “Author” targeted algorithm, coupled with shopper affinity. The model chosen for this strategy was the Attribute Best Seller model, with the Author name selected as the attribute to seed off.

In addition, a dedicated affinity configuration was applied with weight given to the category and publisher attributes, ensuring that the bundle shows the most relevant books of the same author based on the shopper’s affinity with publishers and categories viewed and purchased in the past.

The impact of this minor tweak was instant and significant. As illustrated in the chart below, there was a noteworthy increase in their Key Performance Indicators (KPIs) for their bundle performance:

Click-Through Rate (CTR) saw an impressive lift of 76%.
Items per Thousand Views (IPVm) increased by 40%.
Revenue per Thousand Views (RPVm) spiked by 16%.

Sudden spike in CTR upon refining the bundle algorithm

This case demonstrates how adjusting one aspect of the bundling configuration, in this case refining the bundle algorithm, can significantly drive critical success metrics. Algonomy’s dynamic solutions provided the agility and responsiveness to achieve these outcomes.

2 Use Case 2 – The Power of Compatibility

In tech-related verticals, compatibility between the main product and accessory items is crucial. Our client from the office supplies vertical recognized this and utilized their external data to guarantee compatibility between printers and their associated ink and toners.

With the primary goal of increasing sales, they successfully implemented ‘automatic’ bundles on most categories using Algonomy’s out-of-the-box cross-sell and upsell algorithms. This meant simply utilizing strategies already enabled for their PDP and having Algonomy determine automatically which strategy to play where and when to obtain the best products to recommend in the bundles.

However, when it came to the Printer category, custom solutions were required in order to ensure only compatible cartridges were presented in the bundles.

Using Algonomy’s Data Science Workbench, the client could construct custom algorithms based on their external data. The data uploaded to Algonomy, consisting of lists of compatible product IDs, helped create cross-sell and upsell algorithms.

This approach guarantees that the suggested bundles for printers consist only of compatible ink and toner sets and, at the same time, allows presenting shoppers with bundles of ink cartridges of different colors or yield capacities.

Compared to the regular cross-sell recommendations on these Printer category pages, the results of the compatible bundles were astonishing:

CTR is 200% higher on the bundles, more than doubling the regular cross-sell compatible recommendations.
Items per Thousand Views (IPVm) from the bundles is 162% greater.
Most impressively, Revenue per Thousand Views (RPVm) is 400% higher, quadrupling the revenue from bundles compared to the regular cross-sell compatible recommendations.

This case demonstrates the immense potential of Algonomy’s customizable solution when it comes to creating unique bundle strategies, by capitalizing on data and ensuring compatibility.

“Our previous manual bundle solution was not scalable or sustainable long-term. Algonomy helped implement automated product bundles, leading to a jump from 4% to 80% product coverage, minimising internal maintenance effort and allowing a focus shift to optimisation. We’re really encouraged by the initial results and look forward to building on this together with Algonomy.”

Senior Manager of Conversion Rate Optimisation & Tooling

4 Use Case 3 – Effortless Bundle Implementation and Testing Through Algonomy Portal

Our customer in the health and beauty sector wished to implement product bundles but felt challenged due to resource constraints for backend and front-end development.

They required a solution that allowed them to:

Algonomy’s Dynamic Experiences functionality proved to be a game-changer. It helped the client set up bundles independently, fitting their unique requirements and constraints. For any additional technical skills, our consultants provided the necessary support for fine-tuning layouts or incorporating custom JavaScript, all done seamlessly via the portal.

The Multivariate Test (MVT) capability, intrinsic to Algonomy’s Dynamic Experiences, simplified the process of setting up a control experiment. The client easily configured a 50/50 test to compare the performance of bundle placements versus pages without bundles.

The metrics from their test surpassed expectations, with an impressive lift in Revenue per Visit (RPV) and Average Order Value (AOV) by 8.42% and 8.24% respectively, showcasing statistically significant results with 99% confidence levels.

Results

Overview

Advanced Algorithms for Product Bundling

Bundle Composition, Layout, and Implementation

Use Cases

Get in touch

“The feature is easy to set up and it’s great that it can be tailored to what it is we require, especially when we only want it to show on specific categories!.”

Digital Merchandising Executive

Explore More Resources on Commerce Personalization

See all customer stories

Malaysia Conversational AI

How Cycle & Carriage Singapore turned WhatsApp into its main channel for events, test drives, and high-net-worth engagement

See full story

0 %

Improved lead completion rate

See all customer stories

Looking for a Personalized Demo?

Let’s talk

Riachuelo Sees Nearly 4X Increase in CTRs and 5% Surge in Sales with a Nifty Countdown Widget

Case Study

Riachuelo Sees Nearly 4X Increase in CTRs and 5% Surge in Sales with a Nifty Countdown Widget

Facebook X LinkedIn

Business Value Delivered

0 %

Surge in sales

0 %

Growth in Black Friday Sale fragrance category

0 %

Increase in overall click-through rates

0 x

Rise compared to regular CTRs in other recommendation locations

Client Overview

Riachuelo stands as one of Brazil’s largest and most distinguished fashion retailers. Established in 1947, the brand currently operates more than 300 stores and boasts a growing team of over 44,000 employees. With a history spanning over seven decades, Riachuelo has become a household name, offering a diverse range of apparel, accessories, and home products. Riachuelo’s commitment to delivering the latest fashion trends, top-notch products, and exceptional customer service has solidified its position as the preferred destination for millions of shoppers nationwide.

The Solution

1 The Countdown Widget — A Closer Look

Developed in collaboration with Algonomy, the Countdown Widget is a dynamic and personalized feature that displays targeted product recommendations and a real-time countdown timer. Utilizing AI, custom merchandising rules, and data analytics, the Countdown Widget tailors product recommendations based on user behavior, preferences, and business rules, aligning seamlessly with merchandising objectives for the ongoing campaign.

2 Motivation

Implementing Algonomy’s Countdown Widget at Riachuelo stems from various motivations, aligning with Riachuelo’s commitment to agility, efficiency, and customer-centricity:

Effortless Deployment
Streamlined Experience Management
Efficiency through Reusable Templates
Dynamic Injection for Flexibility in Page Placement

Results

Client background

Solution

Get in touch

“The Algonomy platform analyzes and acts based on behavioral data collected on the website, providing personalized experiences to consumers, which enhances our understanding of customers and drives business results.”

Ana Paula Santos Silva

Business Analyst

Riachuelo

Explore More Resources on Commerce Personalization

See all customer stories

Malaysia Conversational AI

How Cycle & Carriage Singapore turned WhatsApp into its main channel for events, test drives, and high-net-worth engagement

See full story

0 %

Improved lead completion rate

See all customer stories

Looking for a Personalized Demo?

Let’s talk

How a US-based Retailer of Skin Care Devices Achieved 24% Increase in Revenue Per Session with Algonomy’s EngageTM

Case Study

How a US-based Retailer of Skin Care Devices Achieved 24% Increase in Revenue Per Session with Algonomy’s EngageTM

Facebook X LinkedIn

Business Value Delivered

0 %

Increase in clickthrough rate (CTR)

0 %

Increase in revenue per session

0 %

Increase in overall clicks

Client Overview

The client’s mission is to beautifully transform skin through its award-winning devices, which cleanse skin six times better than hands. Hand-assembled at its headquarters, the devices are distributed through prestige retailers, dermatologists, cosmetic surgeons, spas and online at the client’s own ecommerce website.

The Director of Ecommerce and Digital Marketing for the client is in charge of managing customer website experiences to achieve the direct-to-consumer revenue goals for the business. In addition to optimizing traffic, conversion and revenue, the team manages all content, paid media channels, affiliates, search engine optimization and search engine marketing as well as retargeting, email and loyalty programs.

For the client, engaging and educating the new user is a critical objective for the website. When new visitors have their first experience with the brand on the website, they want the site to represent the “knowledge hub of the brand” so they can learn everything—from which device is right for them to what skin care products and brush heads pair best with their chosen device.

Old way

Multiple messages meet multiple needs

The Solution

1 Content and Context Motivate Visitors through the purchase funnel

Having learned about Algonomy through existing partnerships with sister brands, the client decided to use the Engage™ solution to segment audiences, and test and optimize content tiles against key metrics—click through rate and revenue per session.

“Everyone will always have an opinion, but our job is to move from opinions to data-based decisions that show what customers are gravitating toward,” said the client.

“Clickthrough rate may be a function of the creative; revenue per session may be a function of the right message and content. A lot of times we don’t know, and that’s why it’s critical to always be testing.”

Engage™ maps individual shopper behavior against advanced targeting and audience segmentation tools so that marketers can deliver highly personalized campaigns with relevant content. Its ability to automatically target each segment, optimize the most effective creative for that segment, then pass the data back to the business to inform creative decisions for the next round of campaigns saves valuable time and eliminates the need to run hundreds of manual A/B tests to get content personalization right.

After implementing EngageTM, the client has seen significant success in key metrics for users that interact with its home page content tiles, such as a 20 percent increase in clickthrough rate and a 24 percent increase in revenue per session, while also seeing a 35 percent increase in overall clicks.

“EngageTM gave us information on what messages and creative were resonating with customers. We tested 12-15 pieces of content for each customer segment and found two that resonated very well: ‘Find your Product’, which linked visitors to an interactive skin quiz recommendation engine, and a tile with the message ‘Great Skin Starts Here,’ which highlighted our key skin care benefits to our users,” said the client.

With plans to continue testing current content “winners” against new content, the client looks forward to uncovering more learnings and insight from using EngageTM.

“The fact that I can keep testing content and justify why I’m showing it is amazing! I’m confident that these data-driven decisions are helping to move visitors efficiently through the purchase funnel,” they said.

Results

Client background

Old Way

Solution

Get in touch

Director of Ecommerce and Digital Marketing

Explore More Resources on Commerce Personalization

See all customer stories

Malaysia Conversational AI

How Cycle & Carriage Singapore turned WhatsApp into its main channel for events, test drives, and high-net-worth engagement

See full story

0 %

Improved lead completion rate

See all customer stories

Looking for a Personalized Demo?

Let’s talk

Stadium Drives +17% RPV with AI-Optimized Messaging

Case Study

Stadium Drives +17% RPV with AI-Optimized Messaging

Facebook X LinkedIn

Business Value Delivered

0 %

Revenu per Visitor (RPV)

0 %

Conversion Rate (CVR)

0 %

Add-to-Cart Rate

Client Overview

Stadium is one of Scandinavia’s most prominent sports retailers, offering apparel, footwear, and gear across all activity levels. With a strong omnichannel presence across Sweden, Finland, and Norway, Stadium is deeply committed to promoting an active lifestyle and delivering seamless customer experiences both in-store and online.

With personalization already in motion through long-term use of Algonomy’s RecommendTM and EngageTM solutions, Stadium was ready to take the next step by adding social proof to elevate their ecommerce game.

Opportunity

While Stadium wasn’t grappling with specific pain points, a quick pitch and demo of Algonomy’s Social Proof Messaging sparked their curiosity. The promise: real-time social validation layered into the shopping journey to boost CVR and shopper confidence.

As a data-forward brand, Stadium saw potential in experimenting with message types that conveyed what others were viewing, buying, and adding to cart—all in real time. Importantly, they wanted a solution that could scale across five different sites and languages, without compromising on speed or customer experience.

The Solution

1 Social Proof Messaging

Stadium partnered with Algonomy to roll out Social Proof Messaging across item pages on all five of its Scandinavian sites—stadium.se, stadium.fi, stadiumoutlet.se, stadiumoutlet.fi, and stadiumoutlet.no.

Over a 6-week proof of concept (PoC) for stadium.se, the teams tested six message types, each triggered by different shopper behavior signals—views, add-to-carts, and purchases. Each message was displayed in Swedish, with formats such as:

Trendar idag (Trending Today) and Trendar (Trending) based on real-time views
Säljer snabbt (Selling Fast) and Veckans snabbsäljare (This Week’s Bestsellers) based on recent purchases
Populär idag (Popular Today) and Populär (Popular) based on add-to-cart activity

Messages were prioritized by metric, with the system automatically selecting the next best-performing message if the primary one didn’t meet its display threshold. This ensured maximum coverage without compromising message credibility.

The logic and design were optimized collaboratively between Stadium’s team and Algonomy’s solution consultants, taking into account thresholds, time intervals, tone of voice, and aesthetic preferences.

Here is a key use case implemented on the site:

Social Proof Message on Item Page Based on Add-to-Carts Activity
Message displayed: Popular Today

2 Testing and Optimization

The solution was rigorously A/B tested using a 50/50 control vs. treatment split. Key metrics were tracked for products with social proof shown versus those without.

Algonomy’s MVT (Multivariate Testing) tool enabled Stadium to:

Compare message types like Trendar idag (Trending Today) and Säljer snabbt (Selling Fast)
Experiment with different triggers, including product views, add-to-carts, and purchases
Optimize placement, design, and thresholds to maximize visibility and impact

While full AI-powered decisioning was not yet live during the PoC, the foundation was laid for Stadium to eventually automate message selection using real-time performance metrics like RPV, CVR, and ATC rate. This next step is expected to further streamline optimization and reduce manual tuning.

The tests revealed consistent performance uplifts across combinations of messages, time intervals, and placements. The strongest lifts were seen on product detail pages where social proof was visible, validating its influence on shopper behavior.

Results

Client background

Opportunity

Solution

Get in touch

We saw clear results almost immediately after launch.

“Even small variations in message type created surprisingly different uplifts. It’s rare to see a tool this flexible and impactful at the same time.”

Vivian Nadim

Head of Digital CX

Stadium

Explore More Resources on Commerce Personalization

See all customer stories

Malaysia Conversational AI

How Cycle & Carriage Singapore turned WhatsApp into its main channel for events, test drives, and high-net-worth engagement

See full story

0 %

Improved lead completion rate

See all customer stories

Looking for a Personalized Demo?

Let’s talk

Bergfreunde Cuts Campaign Prep Time by 75% Across 12 European Markets

Case Study

Bergfreunde Cuts Campaign Prep Time by 75% Across 12 European Markets

Facebook X LinkedIn

Business Value Delivered

0 %

Reduction in campaign prep time (4 hrs → under 1 hr)

0 %

Faster lead time on changes (1.5 weeks → 2 days)

0 %

CTR uplift on the Birthday campaign

0 %

Revenue-per-user uplift on the Birthday campaign

Client Overview

A pure-play outdoor retailer scaling across Europe, Bergfreunde GmbH is one of Europe’s leading online retailers for mountaineering, climbing, and outdoor equipment. The pure-play online business carries 40,000+ products from 700+ brands, serving ambitious climbers, expedition mountaineers, and urban outdoor enthusiasts across a localized footprint of 12 European markets.

The Challenge

A twice-weekly campaign that wouldn’t scale. Bergfreunde’s flagship promotional campaign — PreisGrounder — was being hand-built directly inside their marketing automation platform, twice a week, for every country. Every send meant rebuilding layouts, swapping products, and re-translating copy: roughly four hours of work and a 1.5-week lead time per campaign. 

With seven markets live and five more on the way, the manual workflow had become a hard ceiling on speed, modernization, and scale — and a blocker to introducing countdown timers, star ratings, and other social-proof elements the team wanted to test.

The Solution

1 Algonomy Active Content

Active Content and Recommend, working in lock-step. Bergfreunde turned to Algonomy Active Content to automate the entire PreisGrounder workflow — from data feed to localized creative for every market — and paired it with Algonomy Recommend to personalize the product picks inside every send. As a Recommend customer since 2015, Bergfreunde already had the product catalog and behavioral data fully integrated, so the team moved fast.

Today, the CRM team simply updates the product feed. Active Content assembles a modern, on-brand email — complete with countdown timers, star ratings, and gender-specific product labels — and pushes localized variants through their marketing automation platform to every country. Recommend handles the intelligence layer, surfacing the right product to the right shopper, every time.

2 Campaigns Powered by Active Content + Recommend

Two campaigns. One automated workflow. Below are the two campaign creatives that ship from the new setup — rendered on mobile, where the majority of Bergfreunde’s shoppers open their email.

Campaign 1

PreisGrounder — Twice-weekly promotional

Campaign 2

Birthday — Personalized via Recommend

Results

Client background

Challenge

Solution

Get in touch

The collaboration has been very positive and constructive. Algonomy’s technology is flexible and powerful — particularly in automating campaign execution and enabling more modern, engaging designs. I am especially pleased with the efficiency gains and the improved scalability of our campaigns.

Martin Hauf

CRM Manager

Bergfreunde

Explore More Resources on Commerce Personalization

See all customer stories

Malaysia Conversational AI

How Cycle & Carriage Singapore turned WhatsApp into its main channel for events, test drives, and high-net-worth engagement

See full story

0 %

Improved lead completion rate

See all customer stories

Looking for a Personalized Demo?

Let’s talk

Consum Cuts Campaign Costs by 60% with Ada Global’s Active Content

Case Study

Consum Cuts Campaign Costs by 60% with Ada Global’s Active Content

Facebook X LinkedIn

The Results

0 %

marketing service provider cost savings for the loyalty team

0 %

reduction in time to prepare a campaign

0 %

reduced in turnaround time in additional communications

About Consum

Consum is Spain’s cooperative with the largest number of members and a leading regional supermarket chain, headquartered in Silla, Valencia. Founded in 1975, Consum has grown into a trusted brand for over 5 million customers, operating a network of 1,000+ supermarkets across six autonomous communities (Comunidad Valenciana, Cataluña, Murcia, Castilla-La Mancha, Andalucía y Aragón). Consum operates a robust benefits program called Mundo Consum, which offers exclusive benefits to its member-customers, including a monthly cashback check and personalized product offers.

Challenge

To personalize the key commerce touchpoints of product recommendations, search, category pages, and content.

Consum aimed to streamline how it delivered personalized campaigns across channels, languages, and customer segments.

The Solutions

1 Monthly Gift Check Emails

Sent mid-month, these emails automatically displayed the customer’s individual cashback amount as soon as it was available in the app, driving immediate engagement and traffic.

2 Personalized Discount Campaigns

At the start of each month, customers received product-specific offers based on supplier-defined segments. Active Content ensured the right message reached the right customer without manual intervention.

3 Localized & Personalized Newsletters

Each customer received a rich, tailored email featuring “My Favorites,” “Cheque Crece,” regional promotions, and a store-specific brochure—all assembled from over 15 localized assets in real time.

Results

Client background

Challenge

Solution

Get in touch

“With Ada Global’s Active Content, we were able to take full control of our campaign execution. It’s given us the speed, flexibility, and personalization scale we needed to elevate how we connect with millions of members every month.”

Santiago Mozas Hernando

Jefe de área Digital de Fidelización, Departamento Socio-cliente y Marketing, Consum

Explore More Resources on Personalized Marketing

See all customer stories

Malaysia Conversational AI

How Cycle & Carriage Singapore turned WhatsApp into its main channel for events, test drives, and high-net-worth engagement

See full story

0 %

Improved lead completion rate

See all customer stories

See How ADA Verify Can Simplify Your Customer Onboarding

Book a Demo

Personalizing Beauty at Scale: How Matas Grew Attributable Sales by 36% with Personalized Recommendations

Case Study

Personalizing Beauty at Scale: How Matas Grew Attributable Sales by 36% with Personalized Recommendations

Facebook X LinkedIn

The Results

0 %

YoY growth in attributable sales

0 %

increase in orders via recommendations

0 %

increase in items sold via recommendations

0 %

growth in total site views

0 M

clicks on recommendations, with improved CTR (1.6%)

Client Overview

Established in 1949, Matas is Denmark’s premier health and beauty retailer. With over 250 stores and Denmark’s second-most-visited ecommerce site, Matas serves millions of customers through both its physical network and robust digital presence. In 2023, Matas expanded its regional footprint by acquiring KICKS, a major beauty retailer across Sweden, Norway, and Finland.

With personalization playing a pivotal role in customer engagement, Matas sought to create a seamless, data-driven experience across all channels—web, mobile, and email. Their long-standing partnership with Algonomy, dating back to 2018, laid the foundation for a phased, scalable personalization program that continues to evolve.

Opportunity

Matas wasn’t looking for just another recommendations engine—they wanted a best-of-breed personalization layer that could unify customer experiences across touchpoints and deliver results at scale. Key business objectives included:

Creating a coherent and personalized CX across channels
Driving online profitability and engagement
Ensuring operational efficiency with fast time-to-market

The Solutions

1 Web & Mobile Personalization

Across home, category, search, item, add-to-cart, and cart/checkout pages, Matas deployed hyper-relevant product recommendations that mirrored campaign messaging and user context.

Key strategies included:

Seamless cross-selling during Add-to-Cart

(For e.g., “More amazing skincare products” or “Bestsellers from the same brand”)

Cart page cross-sells

(For e.g., “Other customers also bought” or “Discounts on your favourite brands”)

Smart replenishment

(For e.g., “Buy again?” and “Your previous purchases”)

2 Email Personalization

Across home, category, search, item, add-to-cart, and cart/checkout pages, Matas deployed hyper-relevant product recommendations that mirrored campaign messaging and user context.

Matas added recommendations to all email journeys and campaigns. With both OOTB strategies and tailored algorithms, marketers could:

Advanced merchandising and configuration controls gave Matas full autonomy to manage everything in-house—no dev cycles needed.

3 Additional use cases reflect the advanced maturity of Matas’ personalization strategy:

Landing Pages & Campaign Pages: These are fully automated and personalized to match promotional campaigns with hyper-relevant product assortments at scale, enabling rapid time-to-market.
Subscribed/Auto-Replenishment Products: De-boosting strategies are intelligently applied to help customers discover new products beyond their routine purchases, adding a layer of thoughtful curation.

Results

Client background

Challenge

Solution

Get in touch

“All I care about is relevance on the customer’s terms—full transparency and real control. Algonomy helps us make every interaction meaningful without compromising trust or customer experience.”

Peter Hestbaek

SVP of Digital Sales

Matas

Explore More Resources on Personalized Marketing

See all customer stories

Malaysia Conversational AI

How Cycle & Carriage Singapore turned WhatsApp into its main channel for events, test drives, and high-net-worth engagement

See full story

0 %

Improved lead completion rate

See all customer stories

See How ADA Verify Can Simplify Your Customer Onboarding

Book a Demo

Older posts

Products

Solutions

Industries

Our Company

Featured article

2026 Guide: Fixing Supply Chain Visibility Gaps in India’s CPG Sector with AI

Resources