Introduction to product recommendations

This is for:


In this article, we’ll introduce you to our Product recommendations programmatic experience and discuss how you can use it to deliver tailored product recommendations across channels.

What is Product recommendations?

Qubit’s Recommendations uses the power of machine learning (ML) to learn patterns in the product catalog and visitor buying and viewing behavior and then create recommendations tailored to the visitor and the moment in the journey.

It includes cross-sell and upsell capabilities and enables merchandisers to leverage data in the Data Store to personalize the user’s journey, influencing engagement, and purchases.

Key features

  • A set of plug-and-play strategies, tailored for various points throughout the visitor journey. These strategies orchestrate the various kinds of data in the Data Store, including collective purchasing and viewing behavior, product similarity, and personal preferences, to create highly relevant recommendations

  • Curation of recommendations by the marketer through a set of merchandising rules to support business goals

  • Promotion of products through recommendations to increase the visibility of products on the site. This is done algorithmically so that promoted products fit with the other products on the page. This is a clear advantage over hard-coded rules that promote products across all pages statically

  • Possibility to connect recommendations with other programmatic experiences, such as Social Proof, which draws on the power of social influence to create urgency and re-assurance, which has a proven track record in increasing the likelihood of conversion

Qubit’s plug-and-play strategies

At Qubit we offer strategies, defined as recommendation endpoints, designed around specific business goals. A strategy for example can be focused on increasing engagement or increasing order value.

Qubit’s plug-and-play strategies are continually optimized by Qubit’s Data Science team to learn best practices for your business and deliver insight that can be fed back into your overall business strategy.

The outcome of each strategy is contingent upon the context where the recommendation is placed. The context where the visitor sees the recommendation is most commonly defined by a page type or channel.

We believe it is important to test and evolve each strategy within a particular context, for example page type, as different points in a visitor journey on a site may merit different strategies for product recommendations.

For example, the strategy to attempt to increase order value on a product page may be different to the one later in a visitor’s journey on a basket page. In testing and evolving our strategies, we exercise control over the strategies and context, thus ensuring we deploy strategies at the point in the visitor’s journey where they work best. This maximizes the positive impact of recommendations on a website.

Each of our strategies comes with a specific combination of algorithms, configurations, and fallbacks and with the exception of trending, popular, recent, and new, each one requires information about the currently viewed product on a page. If that information is not being sent, for example, in a setup that calls the Recommendations API directly, recommendations will fall back to most popular products across a site over the last 30 days.

Engagement (API strategy engagement)

Designed for brands that wish to drive engagement by drawing users further into their product inventories, this strategy is based on a users who recently looked at this product, also looked at an these products logic and is a perfect fit for product detail pages.

Measure: product views

Upsell (API strategy upsell)

Designed for brands that wish to drive upsell on basket or checkout pages, this strategy is based on a users who purchased this product, also purchased these products logic and is a particularly useful strategy for increasing and widening the conversion funnel.

Measure: product purchases

Conversion (API strategy conversion)

By surfacing details of what other users eventually bought after viewing a product, you can encourage users to explore more of your product inventory and reassure them against other user’s shopping habits. Based on a users who viewed this product, purchased these products logic, it is most often used further down the user journey to validate purchase decisions on product detail pages.

Measure: product purchases

This strategy considers views over time to determine which products are truly trending on your site and is ideal for repeat users on their return to your site to highlight the latest product trends from your brand.

Measure: product views

Typically used on a home page or search results pages, these strategies show views from all visitors to surface popular products (computed daily) across your site.

The popular strategy is a great choice when you are looking to offer initial inspiration to first-time users. It is most often used on broader-focused pages such as a home page.

best_sellers_<FEATURE>_<N>_days are more precise strategies that based on revenue and/or volumes sold within the last 7, 28, or 90 days. See Deliver recommendations (Qubit).

Measure: product views


These strategies are ideal for exposing users to newly introduced product lines. Typically used on a home page, they show products added to your catalog within the last 7, 28, or 90 days, ordered by popularity (number of views). See Deliver recommendations (Qubit).

Measure: recently added products


Most effective on order confirmation pages and other pages towards the end of the purchasing funnel, this strategy focuses on the first and second purchases in the purchase cycle to drive cross-selling by recommending products that other users bought next after purchasing the seeded product(s). This strategy will be of particular interest to brands looking to drive retention through more relevant recommendations.

Measure: product purchases

Refer to the following table for details of our recommended strategy use:

Strategy Name Placement


Product detail page


Basket page, checkout page


Product detail page





Homepage, search results page




Checkout page, order confirmation page

Extending with rules

Qubit offers the possibility to extend recommendations through the creation of custom rules. Rules help improve product recommendations by adding a business logic layer that is overlaid on top of our algorithmic strategies and enable marketers, who are often best placed and have the deepest product knowledge to fine-tune recommendations to better align them with key strategies and business goals.

For those interested in using the Recommendations API to deliver rules specific to each request, see Per-request filters.

Recommendations API

Qubit’s Recommendations API offers the possibility to deliver more powerful and personalized recommendations experiences. See Deliver recommendations (Qubit) for a guide to using the API.

We also offer the possibility to deliver product recommendations using one of Google’s recommendations strategies. You can find out more in Deliver recommendations (Google).