The essentials for choosing the right product recommendation strategy

If you’ve ever browsed an e-commerce site, chances are, you’ve been exposed to product recommendations. These machine learning-powered recommendations, designed to suggest relevant products across your site visitors, are used by marketers and merchandisers to drive discovery, increase monetization and reduce exit rates. However, behind every powerful widget are algorithmic decisions, dictating various approaches to recommendations. Primarily referred to as recommendation strategies, these provide the logic behind which item is selected and presented in all digital recommendation widgets.

Choosing the proper strategy for the desired objective is essential to success, and the misapplication of strategies can have serious repercussions. Not only can it cause a loss of revenue, but it also may drive customers to lose faith in both the value of recommendations and your ability to deliver personal, engaging experiences altogether. And with customer experiences increasingly taking over as the key differentiator between online entities, brands must capitalize on the opportunities afforded to them through recommendations, leveraging them to make them a contributing factor to overall success.

Using personalized recommendations is sometimes seen as a swing for the fences, but it doesn’t have to be. While contemplating the most appropriate strategies to apply, every marketer must first consider the context of each experience (i.e. which page to deploy it on) as well as the audience they want to reach (i.e. specific personas or segments). Only then can a suitable strategy be selected and applied, in hopes they ultimately drive revenue. Additionally, with the ubiquity of actionable data insights, different recommendation strategies can be delivered to different audience segments, presenting a great opportunity to connect with visitors on a personal level. 

Modern recommendation engines now support omnichannel experiences, synchronizing recommendations across web, mobile apps, email and in-store touchpoints. If a recommendation is properly matched with a user, it can create a pleasant user experience, increasing the chances of a connection forming between a site and the visitor. And with access to ample user and product information, marketers can do so at scale with ease. However, marketers must strike the right balance, ensuring they have the right insights for the right strategies — such as purchase history for purchase-based recommendations — and don’t overstep any boundaries that may compromise relationships with their customers.

When it comes to product recommendations, there are three major types of strategies users can look to when crafting their plans:

• Global recommendation strategies: These strategies focus on general characteristics and trends across the customer base, offering recommendations relevant to a broader audience. As the homepage is the main entry point, marketers often use these strategies to showcase to new site visitors.
• Contextual recommendation strategies: These strategies consider the current context of the customer, such as the product they’re viewing or the ways they engage with your website, to suggest related to complementary items. These usually perform well on product detail pages or article pages.
• Personalized recommendation strategies: These strategies can leverage customer insights to suggest items that cater to their specific preferences, as well as browsing and purchase history. These algorithms are typically used to better meet the needs of returning visitors, with some designed specifically for new visitors. These strategies can be deployed across pages and screens. Think about category pages displaying and automatically sorting relevant SKUs according to customers’ unique affinities and preferences. Real-time personalization is now standard, with engines adapting recommendations instantly based on in-the-moment context and external signals, such as weather, location, trending topics and more.

Examples of specific recommendation strategies that fall under these three tiers are listed in the table below.

Let’s dive into the various recommendation strategies provided by the top personalized recommendation engine providers, breaking down how they work and when they should be used.

Most Popular

Recommends top-selling products or most-viewed content. One popular recommendation strategy is to display ‘top items,’ or items ranked as ‘highly purchased’ or ‘best.’ Items are scored based on the weighted sum of all interactions, such as purchases, adds-to-cart and product views. The system favors recent interactions over historical ones and updates scores every time a data insights feed is synchronized.

As this strategy usually isn’t based on highly personalized  insights, it’s beneficial when little to nothing is known about a user or when a user displays intent to simply browse around the site. It’s also great for promoting your hottest items, helping your business stand out against your competition. It will assist with and enhance the product discovery experience, helping you market your brand, as well as the popular merchandise it offers.

You can also use “popular in location,” to populate recommendations that are based on what users in a sub-division within a country’s IP address have recently purchased, added to cart or viewed. 

Additionally, using the “popular” recommendation strategy, brands can surface popular products to site visitors. Similar to the “most popular” strategy, products are scored based on the sum of all interactions before being served to users. For example, once a brand identifies the top 20, 50 or 100+ products for sale on the site, it can use this strategy to display any five products in the cohort in a homepage recommendation widget, rather than solely the five most popular products.

One other similar strategy is the more specific “most popular in category” strategy, which not only surfaces the most popular items but only includes items from a specified category. “Trending” can also be used to highlight products or content experiencing a surge in popularity or interest.

You can also filter by “newest arrivals,” which showcases recently added products or content, and ‘seasonal picks,’ which curates recommendations based on seasonal trends and preferences.

Similarity

As its name would imply, widgets powered by a “similarity” strategy display products that resemble the item (or group of items) currently in view, factoring in the item’s popularity. Complex algorithms are designed to ascertain the metrics — using categories and keywords provided from the  feed — resulting in a similarity “score” for each item. Then, the products with the highest similarity scores are displayed to the customer.

While there are many applications for this strategy, one of the most efficient is to place a recommendation widget powered by the “similarity” strategy on a product detail page (PDP). Doing so will not only expose the site visitor to additional products but to products they are likely interested in. Surfacing items similar to a product in view will potentially communicate a business’ ability to understand what the user is looking for, increasing the likelihood of driving a successful sale.

Product recommendations carry specific contextual strategies and can be good for product description pages. Also, if a “just added” recommendation widget can be deployed via popup after a customer adds an item to their cart, consider using these strategies to drive up your average order value, especially if you showcase products that are slightly cheaper than those in a customer’s cart. It empowers customers to make quick purchase decisions, often resulting in upsells.

There is also the “visual similarity” approach, which utilizes deep learning to recommend items visually similar to the viewed product, catering to customer preferences beyond explicit descriptions. This typically works well to recommend similar products a customer may be interested in on PDPs and add-to-cart pages

Bought together

Under this strategy, widgets display items that are frequently purchased together with the item currently in view. If your goal is to pad a visitor’s cart with additional products, using this strategy presents upselling and cross-selling opportunities (for example, suggesting a car charger to go with a new smartphone, sandals for a pair of shorts or socks to go with a fresh pair of sneakers).

The system scores products based on the number of times they have been purchased together in the same transaction, demoting products that are typically purchased with many other items. Additionally, it recommends products that are strongly linked to one another rather than products that have an arbitrary connection to a popular product.

One popular way marketers employ this strategy is for a “complete your look” widget, which showcases a collection of products that complement one another. Additionally, when a visitor adds a product to their cart, using a “bought together” strategy to display recommendations can upsell the customer, encouraging them to make another, well-suited purchase decision.

Viewed together 

This recommendation strategy is dependent on what product a user is currently viewing. The system scores other items based on the number of times it has been viewed with the item in view in a single session. When an item is typically viewed with many different items, the system deems the connection weak, decreasing the likelihood of it being served as a recommendation.

Deep learning

Self-training algorithms typically leverage recurrent neural networks (RNNs) to predict the next best item a customer will most likely engage with, based on other customers with similar browsing or purchasing history. These algorithms can also be designed to engage customers from the very first page view with relevant items, solving the cold start problem.

Recent advances include reinforcement learning and hybrid models that combine collaborative, content-based and contextual signals for optimal recommendations.

Collaborative filtering

One of the most popular recommendation strategies, collaborative filtering bases recommendations on similarities between different users. The system analyzes the site engagement of users similar to a current user — the items they’ve viewed, the products they’ve purchased, the items they’ve added to their carts — and recommends these products to other users displaying similar preferences and intent on any page type.

While collaborative filtering is a popular strategy in the market, research has found that “recently viewed” and “viewed together” algorithms consistently outperform it. Deep learning algorithms are rising in popularity for these use cases, such as those that identify the relationships between different items by looking at product interactions across the user base and recommending the next best item accordingly.

Affinity-based

These strategies allow marketers to make compelling product recommendations when and to whom they matter most. As customers browse a site, interacting with various products, they are exposed to a number of product attributes, such as color, brand, style and more. Recommender systems then use these interactions to identify and infer user affinities and preferences, building rich audiencing capabilities for personalization.

This strategy features a weighted score based on the correlation between user engagement (number of views, add-to-carts, purchases, etc.) and the attributes of products they’ve interacted with. The system then bases its recommendations on these scores and can work in real-time, detecting any preference changes. Often taking form as a “Recommended for You” widget, this strategy is suitable for all page types.

Empathy-Based

An adaptive automatic algorithm that leverages the optimal recommendation algorithm and strategy based on the customer’s state of mind, journey stage and website location.

Recently viewed

When using this strategy, the system recommends the last items viewed by the current user, with the most recently viewed items appearing first. These recommendations are typically based on insights from the last 30 days.

Additionally, a similar approach is the “viewed with recently viewed” strategy, which displays items that are typically viewed in the same session with the last items viewed by the current customer.

Last/recent purchase

This recommendation strategy specifically looks at the most recent purchase(s) a user has conducted, typically within the last year. Ideal for encouraging repeat purchases, it surfaces products a user has purchased that may need to be replenished, like pet food or makeup. A simple and straightforward strategy when deployed, it displays the most recently purchased product by a customer in a recommendation widget.

Bought with

When onboarding offline transaction insights, you can leverage them to power smarter recommendations online. With the “purchased together offline” strategy, the system recommends products that have been purchased together offline with the item currently in view on the e-commerce site. The products displayed in these widgets are scored based on the number of times they have been purchased together in the same transaction, recommending products that are strongly linked to one another and demoting products that are typically purchased with many other items.

Similar to the offline recommendation strategy, a “purchase together online/offline” strategy — using offline transaction insights — recommends products that have been purchased together either offline or online with the item currently being displayed.

When using “purchased with recently purchased,” the recommender system looks at the last items purchased by the current user, suggesting items that are usually purchased together with these recent purchases. For example, when deployed on the homepage, this strategy can show all visitors who have bought an item in the past week complementary items while they are still relevant.

Akin to the “purchased with recently purchased” strategy, the “purchased with last purchased” approach ensures all recommendations are based solely on the most recent purchase completed by the current user.

After you’ve selected a recommendation strategy you want to use for a specific campaign, there are a few more steps to run through during the setup phase. Below is a list of the settings, rules and steps every marketer should cover before setting a campaign live: 

• Name: Name each strategy within your testing platform to distinguish differences between campaigns 
• Strategy: Select the desired strategy for each recommendation test  
• Shuffle results: Option to allow items displayed in widgets to change with every page refresh 
• Filters: Exclusion and inclusion rules marketers can set up for any given campaign 
• Custom Rules: Custom exclusion and inclusion rules marketers can set up based on product properties. A few examples include: 
  • Only include: Only recommend products with a specific property (e.g. items that cost more than $30) 
  • Exclude: Never recommend products with a specific property (such as never recommend items that are on sale) 
  • Pin: Always recommend a specific product first, regardless of the algorithm 

When using predefined filters, the need to apply custom “include” or “exclude” rules is eliminated. These dimensions are more flexible, as they do not require property values to be explicitly specified. Instead, they must match / not match the current property value of the item in view. A breakdown of how to apply these strategies is as follows: 

• With the same property: Ensures recommendations have certain properties in common with the item being displayed 
• With different properties: Ensures recommendations do not have certain, specified properties as the item being displayed 
• With the same category: Ensures the recommended items match the same category / parent category of the item being displayed 

If these dimensions are insufficient, marketers can create custom filter rules, choosing which items to include, exclude or pin in a recommendation widget. 

Additionally, marketers are not limited to a single strategy per recommendation widget; instead, they can use multiple strategies in a single widget to improve performance. For example, on a PDP, marketers can direct half of the slots in a widget to rely on a popularity strategy and the other half to rely on a similarity strategy. Combining these strategies can notably increase conversion rates, identifying the highest yield specific to each product category and maximizing revenue. 

Automated A/B testing and continuous optimization are now built into leading platforms, allowing marketers to experiment with strategies and instantly deploy the best-performing variants. Explainable AI is also increasingly important, with recommendation engines providing transparency on why specific products are suggested.

In case a specific strategy returns fewer items than the number of slots available in a given widget — for instance, only three pairs of sneakers on a site match a user’s preferences and affinities), the system is able to “loosen” any constraints imposed by the algorithm or filters. If this doesn’t solve the issue, the recommendation will put a respective fallback algorithm in place. For example, a “Similarity” strategy can have “Popularity” as its fallback, and a “Purchased with Last Purchase” strategy can have “Purchased Together” as its first fallback and “Similarity” as its second fallback. 

Fallbacks respect filtering rules put in place. For example, if you set up a strategy and put an “exclude items under $25” rule in place, the system will respect this constraint, even if there are not enough products to display in the available slots in a widget. 

Picking a strategy according to the audience 

The optimal strategy for your business depends on various factors, including your product range, available customer insights and marketing goals. Often, a combination of different strategies is most effective, allowing you to cater recommendations to diverse customer segments and contexts. By strategically employing these categories, you can leverage the power of personalization to create a more engaging and profitable shopping experience for your customers. 

Not every strategy will work well for all site visitors. Marketers must be able to discern differences between segments of users and tailor experiences according to their needs and expressed interests. For example, site visitors that browse 5+ products on a retail site each week should be treated differently than first-time visitors that click on a search engine ad. 

Global strategies, like “Most Popular,” are suitable for anonymous or first-time visitors, whereas personalized strategies will help tailor recommendations for your most loyal customers, with whom you have a substantial history of engagement to draw from. Shoppers now expect recommendations to reflect their values, such as sustainability, ethical sourcing and accessibility. Engines increasingly factor these preferences into their algorithms. 

This chart provides a few examples of the different recommendation strategies that suit each type of shopper and scenario. Additionally, deep learning can be a great way to choose the most optimal algorithm when you aren’t sure what the optimal strategy will be: 

Product recommendation strategies vary greatly from one another, and in order to select the right one, it’s important to consider all available options. From purchase-based strategies to global, popularity-based ones, recommendations have the potential to guide customers to what they are looking for, sometimes even surfacing items they didn’t realize they were looking for. Additionally, to effectively deploy recommendations at scale at every step of the customer journey, you’ll need a recommendation engine that supports each of these strategies, giving you the flexibility to customize certain elements and leverage insights for more sophisticated, tailored experiences. Having one in place will not only ease the implementation process but will also optimize performance in real time, ensuring you are constantly extracting the highest value from your recommendations and helping you realize your highest ROI.