Product recommendations are something that nearly every ecommerce retailer has, but very few understand how they actually work. This is down to the fact that the technology behind them is complex and complicated to understand. For this reason product suggestions have been shrouded in mystery and packaged up within ecommerce personalization tools. This enables some businesses to twist the truth about how their relevant recommendations work and what recommending technologies they use.

At Coveo-Qubit we have been developing product recommendation technology for over eight years and we have been part of every development, from the old to the cutting edge. This gives us a unique perspective on how these systems work and we want to share that with you.

In this blog you’ll learn about the differences between machine learning-based recommendations and sequential deep learning. It sounds like a lot of buzzwords but stick with us…we’re talking significantly more revenue.

A Peek Behind the Product Recommendation Curtain

A lot of the mystery behind product recommendations can be due to technology for technology’s sake. However recent developments have genuinely changed the customer experience for the end shopper in a dramatic way. Businesses are always pushing to drive conversion rates and increase their online revenues. Product recommendations are a brilliant way to do this, hence why they are ubiquitous across most ecommerce websites. Your conventional product recommendation tool will increase revenue by roughly 3%, which is important. These conventional systems have not changed in any significant way until very recently. 

Conventional product recommendation tools are based on machine learning models, with the most prominent being collaborative filtering. Cutting-edge systems use sequential deep learning with some collaborative filtering mixed in for good measure.

These systems have sufficed to help try and create dynamic personalized experiences for customers. As visitor expectations have increased, however, these conventional systems are no longer sufficient. The main reason for this is that our understanding of the shopper and the customer journey they take has increased, we now truly understand how unique each person’s journey is.

Customers have distinct preferences, category affinities, and price sensitivities. They browse at different times of day, in various orders and with varying levels of purchase intent. Conventional product recommendations cannot consume and utilize this amount of contextual data and respond with higher levels of relevance.

To do this, your online store needs real-time predictive modelling. 

An illustration shows product recommendations on a search result page

How Do Conventional Product Recommendation Engines Work?

In a nutshell, a recommendation engine looks for patterns in lots of data. The patterns it looks for are which products are similar to each other in terms of:

  • Viewed together by all customers
  • Bought together by all customers
  • Bought after a different product is viewed by all customers

Even though product recommendations use only three key areas, conventional technology providers will tout hundreds of algorithms to achieve the above. Unfortunately, all of this ignoring one very important point: The customer.

By definition, collaborative filtering isn’t tuned to offer one-to-one personalization. Vendors have tried to find ‘hacks’ to make this possible, but that will only get you so far. This is complicated by the fact that most of these machine learning systems (and their extremely data hungry nature) run in batch methods either every few hours or even as slow as daily — far from the real-time needs of today’s customer.

Let’s look at a scenario: customers browsing a blue shirt see a “You may also like” carousel of selected similar products, based on browsing behavior of the masses. Products selected in the “You may also like” carousel by conventional recommendations are typically limited to those that are most viewed best seller or purchased within the catalog and may not be the most relevant to the customer.

Instead, recommendations should be pulling the best products from the entire breadth of your catalog to effectively inspire customers with truly personalized product recommendations. 

Main takeaway: You probably have conventional product recommendations, but they are not as personalized as they should be. Instead, they’re product-to-product.

A graphic illustrates the concept of artificial intelligence

Why Are Deep Learning Relevant Recommendations So Different?

Deep learning is inspired by the makeup of the human brain, using layered sets of algorithms that mimic a neural network

By mimicking the brain, deep learning creates important connections between different items (for example, your products) with less data than machine learning’s collaborative filtering.

These connections can also be made with lots of different interconnecting signals such as:

  • Every aspect of the product itself (i.e., color, size, category)
  • Understanding how the customer got to the product (i.e., referrer)
  • Time spent on a product
  • The order in which products are browsed

The order in which customers view products is a fundamental part of the shopping journey that is too often ignored by vendors offering personalized product recommendations.

The other key benefit to using deep learning recommendations over your conventional product recommendations is the speed at which it can make connections between customers and products, using very little data. This is where the neural network really comes into its own, enabling significantly more of the product catalog to be put to work.

This only matters if it drives better results for businesses and we have found, with our rigorous testing, it really does. We see increases of up to 3% in revenue on top of conventional product recommendations alongside 100%+ increases in engagement.

Main takeaway: Deep learning recommendations offer truly one-to-one personalization, because they’re customer-to-product — not product-to-product.

At Coveo-Qubit, we are data-driven. This enables us to be laser focused on achieving innovation and high success rates for our customers. Generic solutions that treat every customer the same breed generic results. That’s why we’re always at the forefront of new technologies that enable us to drive a truly personalized ecommerce experience. We’re here to make ecommerce better. 

Dig Deeper

Speaking of making ecommerce better, why not read Your Guide to Personalized Product Recommendations in Ecommerce? And while you’re at it, check out How Machine Learning Powers Intelligent Suggestive Selling.

Do your product recommendations lack personalization?
Harness the Power of Artificial Intelligence With Coveo’s Recommendation Engines