Skip to main content

REPORT

Leroy Merlin South Africa builds brand credibility and trust in a new market with guided-selling and deep learning recommendations

Leroy Merlin is a large international business, but its tried and tested e-commerce strategies were not working effectively in a new market. Leroy Merlin South Africa was challenged with raising brand credibility and trust in the Leroy Merlin product offering amongst the local audience. Using Dynamic Yield’s AdaptML deep learning system, they converted low-intent first-time visitors into satisfied customers.

Industry

Financial Services

Capability Used

Personalisation Breeze

32%

of total purchases from recommendations

17%

total revenue from recommendations

1 in 3

items purchased are recommendations

Introduction

Leroy Merlin is a French-headquartered do-it-yourself and gardening retailer serving several countries in Europe, Asia, South America and Africa. It is the third largest do-it-yourself retailer in the world, with an unmatched global presence of 300 million customers. Its business is centred on six main sectors: DIY, building, gardening, sanitary equipment, renewable energy and interior decoration, providing everything a person could need for any do-it-yourself project.

Leroy Merlin strives to empower customers to carry out DIY projects by offering a wide range of products and tools, as well as tutorials, workshops and knowledgeable staff. It was important that they offer a wide range of products at various price points to make DIY accessible to customers with different budgets. In their personalisation journey, they wanted to offer the same level of personalised customer advice that they are known for in-store, to make do-it-yourself projects convenient and stress-free for their customers.

However, when breaking into the South African market for the first time, the company quickly realised it would have to adapt its approach to build authentic connections with new customers. They started their journey with Dynamic Yield in 2021 to maximise the impact of their e-commerce experiences. With Dynamic Yield’s deep learning recommendations and engaging out-of-the-box templates, they were able to drive brand awareness and conversions as they expanded their reputation in this market.

“Dynamic Yield’s deep-learning algorithms have helped us to understand and connect with our new customers and make a name for ourselves in this region.”

Francis Baloyi, eCommerce Leader, Leroy Merlin

Execution

Leroy Merlin South Africa knew that their homepage was product-heavy and quite long. They saw a group of their site visitors were scrolling down endlessly, indicating that they didn’t have a purchase in mind, but that they had a relative intention to make a purchase. The team wanted to engage these users and get them to click onto new pages rather than scrolling randomly on the homepage.

They implemented a guided selling approach, placing a welcome banner below the fold. This banner offers a selection of options to direct users towards potential areas of interest. The banner helped users to identify what they were looking for faster, resulting in more targeted browsing sessions that drove higher purchases and add-to-basket rates.

Welcome to Leroy Merlin, how can we assist you today?” banner with options to view current promotions, the product catalogue, personalised recommendations and to sign into profile.

By adding a navigational banner to the lower homepage after the fold, there was a 3.62% uplift in purchases and a 2.35% uplift in the add-to-basket rate compared to when there was no banner.

This showed the team that they could add more guided selling features to their roadmap, as some visitors are at least medium intent, but they don’t know exactly what they want to buy from Leroy Merlin’s large product catalogue.

Delivering a “Just for You” experience

Leroy Merlin wanted to deliver a tailored experience to users who were entering their site from email or their account profile. This was a good starting point for Leroy Merlin South Africa’s personalisation programme because it utilised context from known users’ browsing history. By focusing on users who are already engaged and have signed up for an account, they could see early success before turning their attention to low intent and new users.

Using stacks of recommendation blocks and dynamic content, they were able to compile personalised pages that show users affinity-based recommendations. These recommendations are served based on customer data for past preferences, off-line purchase history and real-time interactions with the brand. Affinity scores are calculated using select attributes such as category, brand affinity, price range, topic, colour and more. 

New users can also visit the “Just for You” page, including by navigating from the lower page welcome banner mentioned previously. These users are shown current trending products as well as deep learning recommendations based on the NextML algorithm.

NextML is an algorithm within AdaptML, a centralised AI system that automates decision making and adapts experiences according to real-time user behaviour across channels, predicting their next move with unparalleled accuracy.

NextML is a self-training deep learning AI system that adapts the digital experience to each user individually, by extrapolating buying intent from user data and predicting which products they might be interested in. NextML recommends the next best series of products based, adapted to user behaviour as they navigate the site. As a self-learning model, NextML continuously optimises recommendations during the session based on buying patterns, visitor behaviour, location and more.

The team used NextML to specifically promote first-party products where possible, driving their brand reputation for top quality products in the region.

The Just for You page is built on a series of recommendation widgets.

Boosting first-party product sales with filtered recommendations

Leroy Merlin South Africa sells thousands of first-party products directly; however, they also have an online marketplace within their website where third-party products are sold. Almost 70% of products available on their website are from third parties. As these products were sometimes more price-competitive than first-party products, Dynamic Yield helped Leroy Merlin to boost the visibility of first-party products through filtered recommendation algorithms.

As well as focusing the scratch card pop-up on just first-party products, Leroy Merlin wanted to ensure that the product recommendations across its site promoted the quality first-party products that they offer. This was important for them in terms of building brand awareness and trust in a new market, rather than becoming a host for smaller third-party vendors.

On Leroy Merlin South Africa’s homepage, the best seller and trending recommendation widgets promote first party own-brand products.

Cardholders who have a high propensity to spend on travel were sent specific communications and offers for this category.

Increasing conversion rates amongst low-intent visitors

The Leroy Merlin South Africa team also wanted to incentivise visitors to make a purchase rather than browsing with no real focus. They used creative and engaging out-of-the-box Dynamic Yield templates to deploy a scratch card pop-up with offers for discounts on first-party products to website visitors.

The scratch card offer pop-up targeted all users who showed exit intent without making a purchase. The offer was limited to first-party products so that the team could push visitors to view more of their own products and build brand and product awareness in the region.

Just one week after introducing this feature, first-party product sales were up 30%. As one of their most successful website campaigns, Leroy Merlin will next look at a more targeted offering to specific audience segments based on intent levels using empathic personalisation.

Empathic personalisation allows brands to further refine and tailor specific content and campaigns according to where the user is in their conversion journey. These audiences put more of a focus on where the user’s mindset is and where they might be facing hesitation in the conversion funnel rather than other approaches to audience segmentation.

Promoting complimentary products and services

NextML was also used after customers added a product to their basket. Leroy Merlin would also offer complimentary services to that product. For example, if a customer adds a new garage door to their basket, Leroy Merlin would promote relevant garage installation services on the basket page.

This was important for the company to raise awareness of their full service offering in a new market, as many visitors would otherwise not realise that they had the option to book services as well as make product purchases through the retailer.

Guided selling with Shop the Look campaigns

As Leroy Merlin has such a wide range of products in its catalogue, the team sought to add “Shop the Look” features for different areas of the home. This new guided selling feature is also focused on medium-intent web visitors who are browsing to make a purchase but are not focused on a specific product. Visitors who enter the category, in this example landscaping, but go to the category page rather than a specific product section, see the below “Shop the Look” interactive module if they scroll down the category page.

Shoppers can scroll over the products on this page to get inspiration for different home ideas. The module is placed below the fold of the category page, targeting medium-intent visitors who have picked a specific category but are “viewing all” in the category rather than going to a specific section.

The Key Takeaway

Leroy Merlin South Africa’s personalisation journey demonstrates the importance of testing and learning what works with a new audience and that success in a new market might require a tailored approach. Understanding audience intent and mindset in the buying journey is crucial for delivering a shopping experience that moves visitors along the conversion funnel.

Leroy Merlin South Africa’s success is exemplified by the fact that the majority of their site visitors are low intent (as with many e-commerce sites) and yet this audience segment has the highest average order value of all site visitors.

With the power of deep learning algorithms, the Leroy Merlin team was able to capture the immediate attention of their low intent customers with highly relevant recommendations, served through innovative Dynamic Yield templates.