[Guide] Advanced Product Recommendation Tactics to 3x Revenue

Effective recommendations make sales.


Unfortunately, many eCommerce stores slap basic category level or best selling product recommendations on their site and never think about it again.


We can do better.


Today, product recommendation engines are capable of learning about a customer in real-time, changing offers based on customer's behavior.


This guide breaks down how eCommerce product recommendation engines work, best merchandizing practices, and the results you can get through improving your eCommerce recommendations.

Advanced Product Recommendation Tactics to Multiply Revenue

Below are some of my favorite tactics to boost conversions and multiply revenues.

1. Create bundles for top selling products

Bundles are a fantastic way to increase average order value.

Kickstarter campaigns are an excellent source of inspiration. Often, creators only have a single core product. To increase the likelihood of success, they create various tiers of participation.

Often, these add-ons are complimentary products that make the core experience better.

Here is one example. Below, the less expensive base game with a single expansion is offered at $22. It has 247 backers. 

In contrast, the "All-in" bundle with multiple map packs, expansions, and other goodies is offered at $90. It has 1,197 backers. 

Kickstarter bundle up-sale

Another example is Fashion Nova.

Here, they create dynamic bundles based on which product is being viewed, presenting them in a simple recommendation widget.

2. Dynamically present recommendations after add to cart actions

When a customer adds an item to a cart, it is an incredibly strong signal about product affinity. 

You can capitalize on this moment in various ways. One tactic is to present a pop-up with the option to continue to checkout or continue shopping. 


In this pop-up, you can also offer complimentary products. Target does this beautifully with their after add to cart action sequence. Here they present items that are frequently bought together. 

3. Take advantage of seasonality and buying trends

Buying trends offer an excellent opportunity to present more relevant offers even without knowing anything about the visitor. 

Amazon provides a great example.

While I am writing this update, we are two weeks away from Mother’s Day. Simulating a first time visitor, Amazon offers numerous Mother Day offers.

Above the fold they showcase a portal to their "Mother's Day Gift Shop", with a separate call to action positioned in the top right corner to "Shop for Mother's Day Jewelry".

As you scroll down, the next recommendation widget highlights a series of top selling categories in the Mother's Day Gift Shop.


Although Amazon doesn't know what this first time visitor is actually coming to their site for, they recognize there is a high chance they will want to  purchase a gift for Mother's Day. 

4. Utilize Personalization Technology in Your Product Recommendations

Personalization is the most effective tactic on this list. 


Your customers are diverse.

Some are price sensitive. Some care about this brand, while others care about that. There will be first time visitors and returning visitors.

Understanding that your customers are individuals is the first step toward effective product recommendations.

Below, we compare one store's experience implementing product recommendation personalization. 

Personalization often doubles how effective recommendations are.

Dynamic Product Recommendations: Don't use static product recommendations. Click Here to see how Barilliance personalizes recommendations on your home, category, and product pages. 

5. Use demographic data when applicable

Nordstrom showcases another advanced product recommendation tactic. 


Instead of using a more generic “Trending Products” recommendation widget, they use a “Trending Near You”.


This takes advantage of geographic differences, such as seasons and taste. Again, the goal is to create relevant offers without having access to previous behavior. 


Incorporating demographic data helps weed out non-relevant offers. For example, it’s doubtful their customers in San Diego shop winter coats, even in December.

Incorporating demographic data helps weed out non-relevant offers. For example, it’s doubtful their customers in San Diego shop winter coats, even in December.

6. Create specific product recommendation strategies for first time visitors.

New visitors have the lowest conversion rates.


In fact, studying millions of eCommerce sessions, we found returning visitors convert 73.72% more than first time ones.


The reason is simple. You don't know what first time visitors like, making it difficult to create relevant offers.

The “basic” strategy is to present a list of best selling items store wide, in the hopes that you will surface what is important to them.

However, there are a number of proactive tactics you can implement to increase your success.

  • Build trust with reviews - Try presenting top rated products to help establish trust with first time visitors
  • Use buying trends - As mentioned above, buying trends are a great way to present relevant offers to first time customers. 
  • Use demographic data - Likewise, demographic data can prevent offering non-relevant offers. 

7. Extend Product Recommendation Engines Across Channels

Omnichannel strategies increase revenue.

Product recommendations are a key tool to make omnichannel effective. They allow you to create highly targeted offers, using known customer data and match affinities to products.

Advanced product recommendation engines like Barilliance can (and should) be applied across channels. 


This can be done in social, chat apps, or still the most converting channel email



Conversion Focused Email Product Recommendations:


Power your emails with the same omnichannel recommendation engine you use for web, mobile, and brick+mortar interactions. 


Unify your data and create the most relevant experiences possible. Learn more here.

8. Increase Trust with Embedded Social Proof Elements

Conversion depends on trust. 


While the concept of social proof is not new, nor "advanced", it surprises me how few companies use social proof elements in their recommended products. 

Amazon integrates social proof elements throughout their recommendation widgets. 

  • Headline - Using implied social proof and herd mentality with a headline of "Best Sellers"
  • Reviews and Ratings - Second, they showcase a products ratings, giving further security that it is a high quality product.
  • Displayed # of Reviews - Third, they underline a products popularity and give more credence to the ratings by displaying the number of reviews a product receives.
  • Trust Icons - Lastly, they display their Prime Icon, which has built up reputation on automatic two day delivery and Amazon backed fulfillment/customer service.

Types of Product Recommendation Engines

How do Product Recommendation Engines Work?

The purpose of product recommendations is twofold: first, to improve the shopping experience, and second to increase revenues.


Product recommendation systems do this by presenting shoppers offers they are most likely to want.


Engines sift through the tens, hundreds, or thousands of items a store carries, and decide which one best suits this particular user.

Generally speaking, there are three broad techniques engines use to filter through SKUs.

1. Collaborative Filtering Technique

Collaborative filtering uses other user’s actions to predict what another user will like.

For example, if one user bought dresses, but ultimately bought a purse, the software would begin to draw a correlation between these two categories. As more and more users confirmed this association, it would begin influencing which products were being recommended.

2. Content Based Filtering Techniques

Content based filtering focuses on the specific shopper. The product recommendation software tracks a users actions, such as web pages viewed, products clicked on, time spent on various categories, and items added to cart.

Based on this information, a customer profile is created. This profile is then compared to the product catalogue to identify which items to show.

3. Hybrid Recommendations

The best recommendation software actually combines both techniques to give the most accurate prediction. This is how Barilliance works.


By combining both techniques, product recommendation engines are able to apply the "wisdom of the crowd" to prospects before they gather much data. As more information is learned about that particular user, recommendations become more and more personalized based on their session and use history.

Dynamic Product Recommendations: Don't use static product recommendations. Click Here to see how Barilliance personalizes recommendations on your home, category, and product pages. 

Merchandizing Rules

In brick & mortar, stores are forced to choose a single merchandising strategy.

ECommerce stores don’t have this limitation.


Retailers can use personalization technology to create specific merchandizing strategies for any segment of customers. One of the main tools retailers use to accomplish this are product recommendations.


How Merchandizing and Product Recommendations Interact

By default, product recommendation engines work algorithmically. 


However, the best engines allow retailers to "overrule" the software's recommendations in lue of explicit merchandizing rules you set up. 

Exmaples include:


  • Restrict recommendations to only show full priced items 
  • Avoid brand conflicts on particular product pages
  • Prioritize transitioning season items
  • Prevent low in stock items from being shown

Retailers define what rules exist, and when these rules are triggered.


Again, using Barilliance as an example, you can determine customer segments that matter to your business. You can then selectively use merchandizing rules on these various segments. 

As you can see, retailers have the capabilitity to define exactly what audience they want to display particular product recommendation widgets for. 


One of the most profitable ways to segment your audience is through a solid RFM analysis. There are six key segments that you can (and should) be creating merchandizing rules for, including:

  • Whales - Customers who have generated the most revenue for your store.
  • Promising - Faithful customers - Customers who return often, but do not spend a lot.
  • Rookies - Your Newest Customers - First time buyers on your site.

By combining merchandising rules and product recommendations, you can create highly targeted offers.

You can promote best selling items to new site visitors, recently viewed items to returning visitors, and related products based on previous purchase to returning customers. 



Product Recommendation Results & Stats

We performed an in-depth study of Barilliance customers who implemented our product recommendation solution.

The results were incredible.

  • Average Attributed Revenue - 12%. We saw, on average, a 12% lift in revenue from our customers after we implemented our hybrid product recommendation solution.
  • Highest Revenue Improvement - 31%. The highest improvement from a customer was a 31% lift in top-line revenue.
  • Increased Conversion Rate550%. Shoppers who interact with our product recommendations were 550% more likely to end their session with a completed purchase.
  • Personalization Effect - Personalized recommendations were 2.2x as effective as generic "best selling" recommendations. 

Next Steps

Improving your product recommendations are the "low hanging fruit" of eCommerce personalization.


We host free demos for our product recommendation solution. If you would like to discover if we could improve your current recommendations with a hybrid, machine learning approach, click here.