Skip to main content

Leading UK Office Supplies Company Drives Hyperpersonalized Crosssells

Case Study

Leading UK Office Supplies Company Drives Hyperpersonalized Crosssells

Segment

B2B

Challenge

Reducing transaction friction to help customers find the products they want quickly and easily

Product Used

The Results

0 %
incremental revenue uplift
0 %
of Attributable Revenue
0 %
of Attributable Sales through cross-sell using Recommend™

The Overview

The client is an office supplies company that is owned by a European multi-specialist distributor of professional supplies and equipment. They started as a small store in Los Angeles in 1960 and now have operations in 11 countries. They are primarily focused on B2B sales, but also have a growing consumer clientele.

They have been partners with ADA Global since 2017. They chose ADA Global as their personalization engine for our expertise and specialization in the field.

The client’s key objectives are to drive customer engagement and incremental revenue by increasing repeat purchases and relevant cross-sells.

They have made a strategic investment in cross-sell recommendations because they drive up average order values and incremental revenue.

They activated ADA Global’s Recommend™ and Engage™ personalization engines to be able to deliver the right and most relevant product recommendations at various touchpoints of their customer’s journey with their website.

Using Recommend™, the client is able to deliver the right product recommendations on the add-to-cart page, product pages, and even on the homepage.

Transforming Product Recommendations

The platform leverages ADA Global’s Xen AI to provide context-aware recommendations based on both user behaviors and affinities and merchandising parameters. It is able to deliver recommendations based on factors more likely to increase relevance for the customer and revenue for the business.

With over 150 pre-built strategies such as visually similar products, compatible products, cross-sell, upsell, and top sellers, businesses can choose to deploy the strategy that is right for them. In addition, custom strategies can also be created for niche business requirements.

Deploying Cross-Sell Strategies Effectively

The client is keen on making cross-sell work, and for very good reason. The incremental revenue this strategy can drive is remarkable. Of the 10% attributable revenue achieved using the Recommend™ platform, 40% is because of cross-sell. Customers like seeing complementary products after adding a product to cart because it makes their purchase journey easier.

The client uses advanced merchandising to generate compatible cross-sell product lists. They collaborate with ADA Global to build custom strategies using the Data Science Workbench, using compatibility data to recommend complementary products in each product family.

For example, if a customer adds a printer to cart, the recommendation engine dives into the merchandising data to bring up inks and toners that are compatible with the model added to cart.

In addition, they use the replenishment strategy to recommend products that the user has previously purchased and is likely to regularly re-purchase. Based on this algorithm, personalized models are built for customers and the strategy is deployed on the Cart page.

They also use advanced merchandising and purchase co-occurrence strategies to create automated product bundles on the product page. This means they are able to combine products that are complementary to each other (such as printers and inks or pencils and erasers) or frequently bought together, and show them as a bundle with a nominal price markdown to entice customers to buy the bundle and therefore increase AOVs.

The client also combines Engage™ with Recommend™ to show personalized category tiles on the homepage. These category tiles take into account customer affinities, and the images shown on the category tiles are based on the customer’s previous purchases.

Moreover, the client uses advanced merchandising rules in the ADA Global personalization engine to create compatible and alternative product recommendations that can be shared across their enterprise systems via custom data extracts. This helps them create product bundles and relevant recommendations on other channels such as in-store and catalogs.

ADA Global also creates several custom monthly reports for the client—at overall business level and at country-specific levels. These reports help them track and measure the value and benefits of personalization across the customer journey in each country.

The client uses ADA Global’s personalization products on their websites in eight countries because of the platform’s superior ability to recommend the right and most relevant products to customers. These smart recommendations also help the client considerably increase customer engagement and brand loyalty.

ADA Global continues to help the client drive personalization that caters to their business goals and drives conversions up. Currently, they are working with ADA Global to deploy more content personalization strategies via the Engage™ platform.

Content
The Results
The Overview
Transforming Product Recommendations
Deploying Cross-Sell Strategies Effectively
Get in touch

400+ Retailers & Brands Across the World Trust Algonomy

Looking for a Personalized Demo? Let’s Talk.

North American Fashion Retailer: 4% Lift in Conversions

Case Study

North American Fashion Retailer: 4% Lift in Conversions

Segment

Fashion & Apparel

Challenge

Enhance visitor experience and accelerate conversions

Product Used

The Client

  • A leading fashion and apparel retailer with 900+ outlets and operating multiple retail concepts in North America.
  • The retailer offers a very wide range of trendy and affordable clothing items for men, women, and kids.

The Challenge

The retailer had deployed best-of-breed personalized recommendations and personalized commerce search, with both already delivering top notch customer experiences.

The retailer had a big sale coming up followed by the launch of a new collection for the season and wanted to ensure they achieve their sales objectives.

The retailer was experiencing a steady growth in online traffic and over 50% of their audience now constituted Millenials and GenZ. To better serve these customers, they wanted to closely align the online experience with the way young shoppers buy and increase conversions.

Age Demographic

The Solution

To enhance the online experience and accelerate purchase decisions, the retailer chose ADA Global’s Social Proof Messaging. The solution was deployed in just 3 days.

Converge shopper and product data

With ADA Global’s Social Proof Messaging, the retailer was able to easily combine real-time shopper behavior and product data and use it to effectively create a buzz for their products – online.

The retailer was able to display metrics like number of people viewing the product, number of people who purchased an item, current stock availability for popular products – in real-time and personalized to each visitor.

The retailer decided to combine these with reviews and ratings for products to encourage customers to ‘Add to cart’.

Targeted and personalized messaging

The solution provided the retailer the flexibility to define the context and audience that can view the social proof messages. The retailer chose to expose 70% of his traffic across 7 categories to social proof.

Plus, they were able to personalize the message to each visitor based on their previous visit and display real-time purchase data and stock availability to build confidence, create a sense of urgency, and persuade visitors to purchase.

Flexible, self-serve solution

With ADA Global’s social proof, the retailer had the flexibility to display multiple messages, determine the hierarchy and prioritize messages.

The retailer was able to personalize the experience for shoppers with real-time social proof through different stages of the buyer journey whether it is on category page, product detail page or the cart page in just a few clicks without the need for IT intervention.

The retailer used pre-built templates to customize the messages, create variants to test outcomes, control their look and feel and decide where they would appear.

Test and Optimize

The Result

  • The ease and flexibility of ADA Global’s social proof helped them enhance the online experience for visitors by a few notches, and aided in helping build visitor confidence and trust.
  • Ultimately, the retailer realized an incremental 4% increase in conversion and a 6% increase in ‘Add to cart’ with minimal effort.
Content
The Client
The Challenge
The Solution
The Result
Get in touch

400+ retailers & brands across the world trust Algonomy to consistently deliver on their commerce KPIs

Talk to our Social Proof expert today.

eXtra Boosts AOV by 52% with Product Recommendations

Case Study

extra-increases-aov-from-product-recommendations

Segment

Consumer Electronics

Challenge

To increase Conversion Rate and AOV using the right product recommendation strategies

Product Used

The Outcome

0 %
higher Items Per Order (IPO) from recommendations
0 %
increase in Conversion Rate
0 %
higher AOV from recommendations

The eXtra Story

eXtra is one of the most popular consumer electronics and home appliances marketplace in the Gulf region, with both online and offline operations in Saudi Arabia, Bahrain, and Oman. It was started in 2003 by United Electronics Company (UEC).

eXtra now has over 45 stores in Saudi Arabia and 3 stores each in Bahrain and Oman, in addition to three websites serving customers in both English and Arabic. They offer over 12,000 different products, including leading international brands, and cater to over 12 million shoppers.

They also offer comprehensive after-sales service such as extended warranty, free home delivery, product installation, and 24×7 remote assistance through three dedicated service centers across Saudi Arabia.

The Challenge

eXtra has been working with ADA Global for close to seven years now. They realized the need to aid their customers in product discovery early on, and wanted to recommend the most relevant products to customers at every step of their journey. A search for the right platform to put this vision into action led them to ADA Global Recommend™.

The electronics retailer continues to place their trust in the platform because of its proven ability to significantly and consistently improve key metrics such as Conversion Rates, Revenue per Click, Average Order Values, and Attributable Sales.

Personalizing All Path-to-Purchase Commerce Touchpoints

Recommend™ makes it very easy for eXtra to deploy different strategies, assign weights to them as per business KPIs, and decide how and where to display product recommendations on a page.

They use product recommendation placements across different pages on their websites and apps. They optimize the impact of these recommendations by using a variety of recommendation strategies, including but not limited to:

  • Advanced Merchandising Strategy
  • Movers and Shakers
  • New Arrivals
  • Site-wide Top Products
  • Popular Products
  • Category Top Sellers
  • Brand Top Sellers
  • Top Offers
  • Frequently Bought Together
  • Related to Cart
  • Related to Cart Category
  • Recently Viewed

The top five strategies that have worked well for them are: recently viewed, others also viewed (category level), others also bought (category level), advanced merchandising strategy, and personalized as per users’ pageview history.
Here are some examples of these placements:

1 Related Items and Category Top Sellers on the Product Detail Page

2 Popular Products and Top Products on the Category Page

3 Advanced Merchandising Strategy on the Add to Cart Confirmation Page

4 Top Sellers on the Cart Page

The Results

eXtra has seen the Average Order Value go up by 52% when product recommendations are present on a page, versus when there are no product recommendations on a page. Similarly, the number of Items per Order is 50.5% higher when there are product recommendations on a page than when there are none.

The electronics retailer’s Revenue per Click grew by 100%, and they have seen a year-on-year uplift of up to 73% in conversion rates (2020-2021) by leveraging the capabilities of Recommend™.

Here’s a quick summary of the growth:

Looking Ahead

eXtra is keen to leverage more of the capabilities of the ADA Global platform to implement more nuanced product recommendation strategies, such as Advanced Merchandising.

They also plan to explore the features of DeepRecs Natural Language Processing (NLP) and deploy it on their websites and mobile app. They believe NLP will not only give them competitive advantage, but also make it easier for their customers to discover more relevant products as well as niche products.

Content
The Outcome
The eXtra Story
The Challenge
Personalizing All Path-to-Purchase Commerce Touchpoints
The Results
Looking Ahead
Get in touch

“As a customer-first business, we are always looking to improve digital experiences for our customers. Through ADA Global Recommend™, we are able to add value to our customers’ shopping journeys by showing products most relevant to them.”

Imran Khan
e-Commerce Director, eXtra

“Recommend™ has been consistently delivering 5% to 7% conversion rates for us, in addition to higher AOVs and IPOs. This has encouraged us to explore more nuanced product recommendation strategies within the platform. We’re also looking forward to exploring DeepRecs NLP, which will help us further individualize experiences for our customers.”

Shahin Riaz
Head of Product, eXtra

400+ Retailers & Brands Across the World Trust Algonomy

Looking for a Personalized Demo? Let’s talk.

Blue Tomato Leverages ADA Global’s AI-powered Recommendation Engine

Case Study

Blue Tomato Leverages ADA Global’s AI-powered Recommendation Engine

Product Used

Algonomy Personalization Suite:

The Results

0 X
Revenue from Orders With Recommendations
0 %
Increase in Avg. Basket Value

The Client

Blue Tomato is a European retailer for snowboarding, freeskiing, surfing, and streetwear. They own more than 55 shops in Austria, Germany, Switzerland, Finland, and the Netherlands. Their product range has over 400,000 items across 500 brands.

The Challenge

The growing breadth of Blue Tomato’s product range became a challenge for their existing recommendation engine. With Algonomy, they aimed to:

  • Reduce manual effort for merchandising and improving recommendation results
  • Recommend matching items from the same as well as different product categories and collections
  • Personalize on mobile devices as well, overcoming the challenges of a small screen

Move from Segmentation to 1:1 Personalization at Every Customer Touchpoint

Complete, unified commerce personalization
Connect all digital path-to-purchase touchpoints — search, navigation, recommendations, and content — to deliver one personal experience that supports the complete customer journey.
Most comprehensive library of 150+ personalization strategies
Accelerate time to market with our strategy library that ranges from wisdom of the crowd and collaborative filtering approaches to deep learning visual discovery and NLP approaches.
Advanced merchandising
Cross-sell and upsell seamlessly by leveraging product attributes and compatibility data. Create automated recommendations and bundles that take the load off your merchandisers.
Algorithmic decisioning for every user with real-time context
Leverage AI to detect each shopper’s stage in the buying process, and combine it with their affinities to pick the best strategy that delivers the most relevant 1:1 experience while meeting your revenue or engagement goals.
Content
The Results
The Client
The Challenge
Move from Segmentation to 1:1 Personalization at Every Customer Touchpoint
Get in touch

Want to learn more about our commerce solutions or personalization offerings?

The value of the shopping baskets resulting from product recommendations has increased by an average of 20 percent, with an average of one more product purchased by each customer. The numbers apply as well for the recommendations shown on mobile devices, where significantly less products can be listed. But thanks to Algonomy, these are the most relevant.

Andreas Augustin
Head of Digital Customer Experience
Blue Tomato

Explore More Resources on Commerce Personalization

Wine.com Drives AttributeBased Recommendations for Personalization
Food & Beverage US

Wine.com Drives AttributeBased Recommendations for Personalization

See full story
0 %
Reduction in out-of-stock across stores
0 %
increase in revenue

Top Brands Trust ADA Global

Read the Case Study

Leading UK Department Store Increases Sales with 1:1 Personalization

Case Study

Leading UK Department Store Increases Sales with 1:1 Personalization

Segment

Department Store

Challenge

Delivering omnichannel 1:1 personalization to increase conversions and sales

Product Used

The Results

0 %
of attributable online sales
+ 0 %
attributable revenue from winter email campaigns
+ 0 %
clicks from personalized campaigns

The Client

The client is a high-end UK-based department store, with a focus on Fashion and Home categories. They have over 42 stores in the UK, Republic of Ireland, and Australia alongside a growing online business.

They have been trading in London since 1864 and went online in 2001, with their website now offering over 300,000 products and recording over 500 million annual visits. They aim to be trading 70% online by 2025. They are also the UK’s largest employee-owned business with 78,000 partners.

The client has been partners with Algonomy for over five years now.

  • The pandemic changed the focus from offline to online, leading the client to revisit their business goals. Their online business went up by 73% between 2020 and 2021. They realized the potential of digital channels and decided to up their game to adapt to evolving customer expectations and beat competition which was ahead in terms of digital maturity.
  • They aim to replicate their in-store service differentiators on their digital channels by recommending the right products and accessories based on affinities so that customers can make the right purchase decisions and complete their purchases.
  • The client wanted a strong product recommendation engine to support this goal and drive up their revenues and customer engagement by providing hyper-personalized cross-channel experiences across eCommerce, mobile app, email.

They deployed Algonomy’s Recommend™ engine to amplify their efforts to deliver hyper-personalized omnichannel product recommendations at various stages of customer journey.

Transforming Product Recommendations

Algonomy’s Recommend™ aligned perfectly with the client’s requirement—that of targeting customers with the right recommendations on multiple channels based on a combination of user purchase data and merchandising data. The client uses the recommendation engine on their website, mobile app, and in email campaigns.

With Recommend™, the client was able to replicate the in-store experience that service partners would provide customers—suggest suitable alternative products, recommend the right complementary products, and help customers make the right buying decisions.

The platform is able to respond to the behaviors and affinities of individual customers in real time in addition to using historical data, including in-store purchase data, which allows Recommend™ to get a 360 degree view of the customer across all channels.

This helps the engine build rich product recommendation models and show the right recommendations at different points of the customer journey, such as after a product is added to cart, upon cart or browse abandonment, and in personalizing emails.

Recommend™ leverages Algonomy’s Xen AI to provide context-aware recommendations and continuously optimize weights and parameters to increase relevance and revenue for each customer. Marketers can choose to deploy various configurable strategies such as visually similar products, compatible products, cross-sell, upsell, top sellers, and Wisdom of Crowd.

How Recommend™ Helped Them Achieve Their Goals

With Recommend’s out-of-the-box strategies such as Similar Items, Top Sellers, Frequently Bought Together, and Configurable Strategies, the client was able to create individualized product recommendations for their customers.

Some of the ways in which these functionalities were used are:

  • When a customer adds a product to cart, an add-to-cart confirmation pop-up appears, with a cross-sell strategy that displays complementary products based on the purchase co-occurrence data from the bespoke report.
  • Product and category recommendations are placed in search boxes based on the user’s recent searches.
  • Emails in the client’s retargeting campaign contain product recommendations based on the individual customer’s affinities to a brand or style or product family.
  • Upon cart or browse abandonment, emails are sent to customers with recommendations of products alternative to or similar to the ones they viewed on the site.
  • The client sends post-purchase emails to their customers, containing recommendations of products complementary to the ones the customer bought most recently.
  • When a customer signs up for notifications for products that are out of stock on the website, the client runs an email campaign around it. These emails contain not just alerts about the product in question but also recommends alternatives and similar products they could consider instead. The same strategy is also used on the website, where alternatives to out-of-stock products are shown in a panel on the product page.

Being able to constantly recommend the right and most relevant products to customers—whether using similar products, compatible products, Wisdom of Crowd, or affinity-based products strategy—the client is able to increase revenues of personalized email campaigns by over 350% and increase the overall online revenue by over 2%.



 

Algonomy creates several bespoke reports for the client’s Analytics department; one of them is purchase analysis by Buying Group (main category) and Buying Office (sub-category within each main category). Using this data, they are able to gather more focused insights for each business unit.

Algonomy continues to help the client create strategies to suit their business goals and add value to their marketing and optimization campaigns.

Content
The Results
The Client
Transforming Product Recommendations
How Recommend™ Helped Them Achieve Their Goals
Get in touch

Explore More Resources on Commerce Personalization

Wine.com Drives AttributeBased Recommendations for Personalization
Food & Beverage US

Wine.com Drives AttributeBased Recommendations for Personalization

See full story
0 %
Reduction in out-of-stock across stores
0 %
increase in revenue

400+ Retailers & Brands Across the World Trust ADA Global

Looking for a Personalized Demo? Let’s talk.

HP Personalizes the First Boot Experience and Beyond With ADA Global’s AI-powered Content Personalization Platform

Case Study

HP Personalizes the First Boot Experience and Beyond With Algonomy’s AI-powered Content Personalization Platform

Segment

Consumer Electronics

Challenge

To create a personalized relationship with each customer from the moment they first use their new HP device.

Product Used

The Outcomes

0 %
increase in engagement as compared to the generic template
0 X
increase in minutes of use when the welcome content was personalized

The Client

HP (#20 on the Fortune 500) is one of the world’s largest computing companies, creating technology to make life better for everyone, everywhere. The company’s mission is to engineer experiences that amaze, and HP produces more devices for more customer segments than anyone else in the industry.

The Challenge

HP’s massive innovation and scale bring about a massive challenge: how to establish meaningful customer relationships when faced with a large product portfolio and millions of users around the globe.

Since the majority of HP devices are sold through retail channel partners, HP doesn’t control the customer experience or have a direct customer connection at the point of sale. However, they do own the ‘first boot’ – that critical moment when a consumer first uses their new device – and the subsequent customer journey through usage and discovery.

Drilling into the first boot experience, HP’s research found that robust product knowledge and software are major contributors to satisfaction, but pre-installed software and wizards are too generic to meet consumer needs. The company also found that the more customers spend time and explore, the happier they are with the new device and more likely to recommend to others:

  • 90% of customers want to do more with their PC
  • 70-80% of user satisfaction is generated at first boot
  • 44-47% dissatisfied with pre-installed software experience
  • Software drives 50% of top 10 customer wants in next device

Armed with these findings, HP looked to reinvent its approach to the first boot experience and beyond. Instead of treating every customer in the same way, HP wanted to provide a personalized experience to inspire, engage and assist customers in getting the most possible from their new device.

HP set strong criteria: the personalization strategy would need to scale to millions of customers without losing relevance; it needed to seamlessly integrate with HP’s existing and future product marketing assets; and it should automatically optimize in real time as new data and content entered the system.

The Solution

HP turned to Algonomy Engage to create HP Jumpstart, a trusted personal companion app that delivers a fully personalized content experience. Using advanced AI, the app engages new and returning customers with dynamic content that shows exactly why their particular product is spectacular. HP Jumpstart points to the accessories, software and services needed to meet an individual’s goals and anticipates evolving demands over time.

How It Works

Beginning at first boot, HP Jumpstart takes users through a series of nine dynamic screens and up to 30 content tiles that connect them with the most relevant information based on what they want to achieve with their new device.

Using advanced AI, every screen and every flow is personalized in real time from thousands of potential messages and differs by customer, segment and geography – presenting the most relevant experience from millions of possibilities. When the customer returns to the app, additional screens and suggestions are available based on up-to-the-moment goals, preferences & behavior.

For example, a U.S. customer buying a premium laptop may be immediately enticed to “Watch Netflix anywhere with a 360-degree hinge” or “Charge your phone from your laptop even when it’s powered down” – essential features that HP had no way to communicate in the past. Alternatively, for a hardcore gamer with a new desktop, HP Jumpstart can take on a totally different complexion with the personality, look and feel of what the HP gaming brand is all about.

Behind the scenes, Engage leverages nearly 300 contextual data attributes received by the Jumpstart app to power a dynamic, personalized content experience based on what is most germane to each customer segment. Advanced machine learning and AI maps individual customer behavior against advanced targeting and audience segmentation tools to display the right content within each screen – as well as determine the correct screens and flow.

Each HP Jumpstart experience is continuously – and automatically – optimized with advanced machine learning that eliminates manual A/B tests. All content is served directly from HP’s Content Management System, allowing HP to use every asset while relying on Engage to scientifically optimize customer response.

Behind the scenes, Engage leverages nearly 300 contextual data attributes received by the Jumpstart app to power a dynamic, personalized content experience based on what is most germane to each customer segment. Advanced machine learning and AI maps individual customer behavior against advanced targeting and audience segmentation tools to display the right content within each screen – as well as determine the correct screens and flow.

Each HP Jumpstart experience is continuously – and automatically – optimized with advanced machine learning that eliminates manual A/B tests. All content is served directly from HP’s Content Management System, allowing HP to use every asset while relying on Engage to scientifically optimize customer response.

The Result

Within six months of launching the Jumpstart companion app, HP has rapidly expanded Jumpstart to millions customers worldwide, and expects this to be the company’s largest direct customer channel by the end of the year. The new companion app has yielded greater than 30% increase in engagement as compared to the generic template HP used in the past And HP continues to record measurable boots in customer volume and quality of engagement, including significant increases in minutes of use each month and average monthly CTR.

HP continues to take advantage of new opportunities to use Engage to accumulate customer insights while delivering a personalized relationship the across the customer lifecycle. Ultimately HP plans to use personalized content to improve all aspects of its business: from awareness of devices, accessories and services through contextual help and predictive support for established users.

Content
The Outcomes
The Client
The Challenge
The Solution
How It Works
The Result
Get in touch

“We want to tell the customer why their HP product is awesome – and make sure they are getting everything they need out of their purchase. Engage takes on the heavy lifting of determining when, where and how to get these messages to the customer in way that is helpful, not obnoxious. We provide the content options, and Algonomy takes on the task of figuring out the right message and time to captivate the customer.”

Aron Tremble
Sr. Director of Software Experience & Products – Personal Systems
HP Inc.

Explore More Resources on Commerce Personalization

Wine.com Drives AttributeBased Recommendations for Personalization
Food & Beverage US

Wine.com Drives AttributeBased Recommendations for Personalization

See full story
0 %
Reduction in out-of-stock across stores
0 %
increase in revenue

400+ Retailers & Brands Across the World Trust ADA Global

Looking to hyper-personalize the content experience for your customers? Let’s talk.

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

Segment

Apparel, Fashion

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

The Client

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.

Content
The Results
The Client
The Challenge
The Solution
Almost a Decade of Compounding
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.

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

Segment

Food & Beverage

The Results

Martin & Servera validated Retail Media as a scalable revenue stream using ADA Global’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

The Client

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 ADA Global, 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 ADA Global setup, the team built a custom campaign planning tool to complement it. Together with ADA Global, 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 ADA Global 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 ADA Global

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.

Content
The Results
The Client
The Challenge
The Solution
What’s Next for Martin & Servera and ADA Global
Get in touch

Explore More Resources on Commerce Personalization

Wine.com Drives AttributeBased Recommendations for Personalization
Food & Beverage US

Wine.com Drives AttributeBased Recommendations for Personalization

See full story
0 %
Reduction in out-of-stock across stores
0 %
increase in revenue

Your Retail Media program starts here.

Wine.com Drives AttributeBased Recommendations for Personalization

Case Study

Wine.com Drives AttributeBased Recommendations for Personalization

Segment

Food & Beverage

Objective

Quickly develop, test, and measure innovative new recommendation strategies

Product Used

The Results

Using Algonomy Recommend™, Wine.com tested a “similar products” strategy that drove $5 per click, becoming one of their best strategies in terms of revenue per click.

The 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 ADA Global 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 ADA Global 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 ADA Global’s Hadoop instance.

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

Content
The Results
The Overview
The Multi-Attribute World of Wine
From Concept to Deployment to Production in Hours
Similarity Spells Success
Get in touch

“We now have the ability to come up with algorithms on our own, create new placements and implement strategies immediately.”

Cam Fortin
Sr. Director of Product Development, Wine.com

Explore More Resources on Commerce Personalization

Wine.com Drives AttributeBased Recommendations for Personalization
Food & Beverage US

Wine.com Drives AttributeBased Recommendations for Personalization

See full story
0 %
Reduction in out-of-stock across stores
0 %
increase in revenue

400+ retailers & brands across the world trust Algonomy to consistently deliver on their commerce KPIs

Looking to hyper-personalize all commerce touchpoints? 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

Segment

Specialty – Health & Beauty
Specialty – Books & CDs
B2B – Office Supplies

Objective

Grow sales by increasing Items Per Order (IPO) and Average Order Value (AOV) with product bundles.

Product Used

Business Value Delivered

0 %
Click-Through Rate
0 %
Items per Thousand Views
0 %
Revenue per Thousand Views

The 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 Ada Global 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

Ada Global’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

Ada Global’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

Ada Global-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 Ada Global’s Dynamic Experiences, this burden is lifted. Entire bundles can be designed, created, and added to your site directly from the Ada Global portal, reducing the operational demands on your team.

In summary, Ada Global’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:

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

This case demonstrates how adjusting one aspect of the bundling configuration, in this case refining the bundle algorithm, can significantly drive critical success metrics. Ada Global’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 Ada Global’s out-of-the-box cross-sell and upsell algorithms. This meant simply utilizing strategies already enabled for their PDP and having Ada Global 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 Ada Global’s Data Science Workbench, the client could construct custom algorithms based on their external data. The data uploaded to Ada Global, 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:

  1. CTR is 200% higher on the bundles, more than doubling the regular cross-sell compatible recommendations.
  2. Items per Thousand Views (IPVm) from the bundles is 162% greater.
  3. 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 Ada Global’s customizable solution when it comes to creating unique bundle strategies, by capitalizing on data and ensuring compatibility.

3 Use Case 3 – Effortless Bundle Implementation and Testing Through Ada Global 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:

  • Create bundles with the look and feel of their Product Description Pages (PDPs)
  • Restrict the bundle offerings to certain categories
  • Test bundle performance against a non-bundle PDP variant

Ada Global’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 Ada Global’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.

The Conclusion

This use case underscores Ada Global’s ability to facilitate bundle implementations even when resource and development constraints exist. It stresses the flexibility and independence our portal provides, allowing clients to execute and test their unique merchandising strategies simply and confidently.

Lastly, it underscores the potential for impressive revenue growth and an increase in order averages with the implementation of thoughtful and well-executed bundling strategies, proving how Ada Global’s Recommend™ can enhance the client’s eCommerce ecosystem.

Content
The Results
The Overview
Advanced Algorithms for Product Bundling
Bundle Composition, Layout, and Implementation
Use Cases
The Conclusion
Get in touch

“Our previous manual bundle solution was not scalable or sustainable long-term. Ada Global 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 Ada Global.”

Senior Manager of Conversion Rate Optimisation & Tooling

“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

Wine.com Drives AttributeBased Recommendations for Personalization
Food & Beverage US

Wine.com Drives AttributeBased Recommendations for Personalization

See full story
0 %
Reduction in out-of-stock across stores
0 %
increase in revenue

400+ retailers & brands across the world trust Ada Global to consistently deliver on their commerce KPIs

Looking to drive revenue growth with bundles? Let’s talk.