What is machine learning and why does it matter for UX/UI designers?
If you’re a designer and find your eyes glazing over when people start talking about AI in the tech world, you’re not alone
Many helpful and exciting things are happening around machine learning, with even more compelling possibilities on the horizon. While machine learning, or AI, is complex, its basic concepts can be understood by data scientists and UI designers alike, and that understanding could lead to significant innovation in the future of app and web design.
What is machine learning and how is it used?
Simply put, machine learning analyzes data to make predictions. Artificial intelligence, which is commonly swapped for machine learning (though machine learning is actually a subset of AI), uses information about each user collected through various methods, such as browser cookies or the user’s activity on the website. Patterns are then found within that data, which is used to make predictions about the user’s needs and behaviors.
A simple but typical example of a machine learning concept is linear regression. Think of your intro to statistics class, where you drew a line of best fit on a graph with an independent and dependent variable:

Linear regression models the relationship between two things by analyzing a significant amount of data about those variables and fitting an equation to them. For example, imagine that linear regression shows a relationship between the number of items in a user’s cart and the number of reviews they read. Then, when it’s identified that an active user is adding a lot of items to their cart, reviews can be displayed more prominently than other information to improve their experience and meet their specific needs.
There are two types of learning algorithms used to make sense of all the collected data: supervised and unsupervised. Supervised learning algorithms learn a relationship between an outcome and data (like figuring out behaviors of those who made a purchase), while unsupervised learning algorithms discover patterns (like grouping users based on their actions).
As you can imagine, training algorithms to compare outcomes and discover patterns is much faster than humans doing the research, which makes a lot of exciting things possible. Many companies currently utilize machine learning to personalize the information architecture to make it more helpful for their users. For example, Google uses AI in Gmail to label emails (social, primary or promotional) differently based on the user. Machine learning learns from your past emailing habits to know what would be classified as a primary email for you, while that may be different for me based on my past behavior.
Or, do you ever use Google Photos to find a specific picture you took of a person or thing? That’s machine learning, organizing your photos into helpful categories like person, place or even objects — I recently found a picture from years ago that would have taken ages to find by scrolling, but I found in ten seconds because I remembered there was a bench in the picture and I typed “bench” into my Google Photos search. Delightful!

The future of information architecture + machine learning
AI is clearly a super helpful tool when it comes to designing information architecture. The possibilities for tailoring a user’s experience specifically to their needs are endless and very exciting! Machine learning’s ability to group users based on common behaviors can help designers better understand the different consumers using a product and create more accurate personas.
Different user flows could be created based on these personas, and AI could tailor the user’s experience on a website based on what works best for that type of user. Designing a new user flow for each type of user would also be quite time consuming, so, instead, designers could create components and AI would dictate the user flow by combining components based on the user’s needs.
Imagine getting on a site, and based off of what machine learning already knows about you plus your current behavior on the site (number of times you click, what you type in the search bar, etc), the site evolves and presents information specific to your behaviors and needs to help you more efficiently accomplish the task you set out to do. As designers, we will have the opportunity to get creative with how we utilize this powerful tool in the information architecture we design.
Our ability to use machine learning to its fullest to create the most useful products will depend on our ability to collaborate. Designers, data scientists and programmers will need to understand the usefulness of AI and share a common language and vision. As whole teams and not just programmers are involved, a cohesive, personalized experience will be more of a reality for users. If designing intuitive and helpful products is our ultimate goal, there has never been a better time for further exploration than now.