Machine Learning for Personalization
 

Artificial intelligence (AI) and machine learning are woven into the fabric of our everyday lives today. Often for huge benefits.

Algorithms direct the flight patterns we depend on to keep us safe during air travel. Natural language processing (NLP) powers our interactions with Siri and Alexa. Machine learning drives the curation of our Netflix suggestions and the contact tracing that helps us combat Covid-19.

On the other hand, whether the decisions behind the algorithms driving groupthink in our social media feeds and Google searches or the biased data reinforcing disparities in hiring, AI and machine learning aren’t always beneficial.

As consumers, citizens, and professionals, we should all have an understanding of the ways AI and machine learning are being put to use, how they affect us, and what benefits they provide. In this blog, we consider the role of AI and machine learning in personalization. By grasping how machine learning is being put to use to drive personalization, specifically within digital customer experiences, you’ll be better equipped to take advantage of this exciting technology for massive benefits in your organization.
 

The Personalization Imperative Remains

But first, let’s note this — personalization isn’t going anywhere. Once a luxury, personalization has become a baseline service in today's digital economy, one the vast majority of consumers appreciate:
 

• 90% find marketing personalization somewhat or very appealing 
   
• 80% are more likely to make a purchase from a brand that offers personalized experiences
   
• 72% say they only engage with personalized messaging
   

Consumers’ love for personalization makes sense. We all embrace experiences that offer us value, and this means being treated like the individuals we are. All businesses today must look for opportunities to show customers they understand their interests, preferences, and intent by delivering relevant content and products to ensure they’re not wasting their customer’s time.

Unfortunately, getting a personalization program up and running is no simple task. Enter machinelearning, whose algorithms can support, automate, and accelerate the process.
 

AI and Machine Learning

Second, let’s clarify some terms.

Artificial intelligence (AI) refers to the broad arena of techniques used to get machines to perform tasks that appear intelligent. Machine learning is a subset of AI.

Over the past couple of decades, machine learning has become a central focus of AI research due to its success in completing cognitive tasks that, less than a century ago, seemed impossible — beating humans at complex games such as Chess, Go, and Jeopardy, driving cars, translating languages, etc.

But neither machine learning nor the other AI methods can currently begin to compete with humans when it comes to improvising, formulating strategies, communicating empathetically, imagining novel situations, inventing new products, and the list goes on.

Machine learning and AI can support some tasks and completely automate others, but machines won’t be displaying creative intelligence, let alone consciousness, any time soon. They definitely don’t mean the end of marketing. No one knows their customers like a brand does, and every brand relies on their employees when it comes to empathetic listening, messaging, and service. AI can detect trends but completing the circle of powerful customer experiences requires a human element.

(This is why, incidentally, some people prefer to use terms like intelligence augmentation (IA) instead of AI.)
 

Machine Learning Techniques for Personalization

While machine learning can feel like magic, the truth is it’s simply statistical and probabilistic models put to work toward a (usually) defined end. Machine learning analyzes large datasets to identify trends. From this, it can extrapolate what’s most probable to happen or what type of experience is most likely to lead to a certain result.

Of course, while it’s not magic, it’s not exactly simple either.

Here are some of the most common machine learning methods used for personalization and what they’re used for:

Regression Analysis

Linear regression could help discover which pages are most likely to lead to a conversion. Logistical regression could be used to discover the best follow-up actions for an abandoned cart.
 

Association

From Netflix to Amazon, this method is a critical tool for building out recommendation engines. Based on your purchase of Dan and Chip Heath’s The Power of Moments, for example, Amazon’s machine learning recommends Seth Godin’s Permission Marketing.
 

Clustering

Clustering algorithms are a great tool for grouping customers into segments.
 

Markov Chains

Can analyze a user’s real-time website behavior and make navigation predictions based on it, which can be used to personalize their experience.
 

Deep Learning

From the natural language processing (NLP) that powers Siri and Alexa to determining the value of possible direct marketing tactics to segmenting audiences for mobile advertising, deep learning is where much of the most exciting work in machine learning has been done in the last couple of decades.

Most machine-learning engines use a combination of these methods to analyze data and offer insight.
 

Getting Started with Machine Learning in Personalization

It’s important to have a working knowledge of what’s under the hood, but you want to get the
machine learning engine started for your personalization program. The following are not linear steps to take. Your program will be unique depending on your market, size, and in-the-moment goals. But keeping these suggestions in mind as you begin imagining, designing, and creating your program will streamline the process significantly.
 

Keep it User-Centered

The user is always the place to start. You know your business goals, and, hopefully, you’ve aligned them with your web goals. (If not, check out this article on Engagement Values.) With these goals in mind, you can start looking for various ways to improve the user experience. What are the critical points of interaction? How can you remove friction or better direct a user toward a specific action?

Keeping your user’s needs front and center and letting empathy drive your use of machine learning and AI is a great way to ensure you’re offering value versus just using the shiny new thing.
 

Know Your Rules

You can (and probably should) use personalization across the entire web journey. This can take many forms, personalized search being one great example. There are, however, four broad categories of personalization rule types.
 

1. Contextual

Contextual rules personalize experiences based on known facts about a user, such as Geo IP address or the channel of entry into a site.

2. Explicit

Some visitors to your site will self-identify by filling in a form for a discount, giving you an email, etc. Explicit rules personalize experiences for these known visitors by, for example, using data from previous page views and conversions to assess the most likely content the visitor is looking for.

3. Implicit

When you don’t know who a user is, implicit rules can use pattern and persona matching to personalize experiences based on the actions anonymous users take on your site.

4. Custom

While requiring further development, custom rules can personalize using anything you want.

AI and machine learning can support all of these rules, but some solutions will require you to determine which rules you want to implement where and when.

Start Small

Chances are my Netflix queue, and your Netflix queue has at least one overlapping movie or TV show suggestion. But this movie or TV show probably looks different in each of our queues. While I love comedy, you’re (let’s pretend) a huge action fan, and Netflix uses this knowledge to tailor the image it places on the recommended movie or TV show.

Varying images is a relatively easy thing to do, but it’s a subtle way to increase the likelihood we’ll watch the suggestions and stay engaged.

Likewise, you can start small with your machine-learning personalization program.

For example, try offering 5 different homepage banners, each tailored to a different persona, and let a machine learning algorithm determine who sees what. Or make variants by switching up any of the elements typically found in marketing assets: headlines, subheads, images, formatting, color, copy, call to action, etc. The point is you can and should start small and build on quick wins.

First Things First — Determine Your Solution

We created an ebook to help everyone who has begun or is looking to begin their personalization journey: Path to Personalization: The 9 keys to driving stronger relationships. The nine keys include making personalization a business priority, establishing your team, outlining your audience and their journeys, and more.

But even with all nine keys in place, implementing machine learning in your personalization strategy from scratch can be a huge lift. This is why it’s critical to choose the right solution. The right one will do the machine learning heavy lifting for you, helping you keep your team as lean and nimble as possible while getting all the benefits of machine learning and AI.

We recently introduced Sitecore AI Auto-Personalization Standard. Simply toggle a switch to turn it on, and it identifies visitor trends, creates customer segments, and modifies page elements to deliver a personalized customer experience. Create one of the above rules, and Sitecore AI will tell you which variation of content is most likely to drive engagement for each customer. Sitecore AI Auto-Personalization automates 1:1 customer experiences. Its sophistication, ease-of-use, and effectiveness helped it win the 2020 Content Marketing Award for Best use of Content Involving Artificial Intelligence for its work with Microsoft's Partner Network.

Sitecore AI Auto-Personalization Premium is available for customers who want unlimited personalization. It also provides an AI insights dashboard, which includes audiences identified from historical and daily data. This dashboard is a great way for marketers to see what’s connecting and what’s not, so they can make changes to the assumptions driving the AI that’s driving customer experiences.

 

For original Sitecore content, click here.