You know the unsettling feeling you get when an ad for a super-specific item you searched for maybe once just mysteriously appears on your Instagram feed? You might ask yourself, How did they know?! Well, the answer is recommender systems, algorithms that use data about products and users’ preferences to make recommendations for the best options to choose.

Recommender systems make up a uniquely challenging (but exciting!) area of artificial intelligence. Whereas a predictive machine learning algorithm is designed to come up with one correct answer, recommender system algorithms are preference-based. As a developer, you need to carefully consider human emotion, behavior, ethics, and logic when building a recommender system.

The thing is, recommender systems are not meant to freak out users — quite the opposite, actually. Recommender systems use a handful of techniques to capture users’ interests and tastes, and help them make decisions about everything from what to buy to who to date.

In our new path Build a Recommender System you’ll learn how to use Python and machine learning to create a recommender system. You’ll also get to know the differences between various recommender system techniques, and will understand how to measure the success of a recommender system. Read on to learn more about the elements that make a recommender system good — and sometimes too good.

Factors that make a “good” recommender system

A recommender system performs well if it strikes the right balance between randomness and specificity — if a recommender system suggests something that’s too specific, it can feel off-putting to a user. When you’re building a recommender system or imagining how you might implement one, you have to keep these  factors in mind.

Relevance: This might sound obvious, but it’s important that recommender systems make recommendations that are relevant to the user, meaning it’s very likely that a user will like what’s put in front of them. For example, a dog owner who only buys dog food or browses dog toys on an online pet retailer shouldn’t get recommendations for, say, bird seed or fish tanks.  

Novelty: On the other hand, recommender systems should present recommendations that a user hasn’t seen before so they can discover more items that are relevant to their interests. Going back to the dog owner example, if they’re only getting recommendations for the most purchased or highest-rated dog foods, the user might not be satisfied with their experience shopping with the retailer.

Serendipity: People are typically delighted when recommender systems make recommendations that are unexpected but relevant. The dog owner in our scenario might get a recommendation for grooming tools or dog clothing, items that they haven’t shopped for, but would presumably like given their interests and previous shopping activity.

Diversity: Having a diverse array of items to offer users increases the chances that the user will like at least one of them. Back to the pet retailer: If a pet owner always buys one brand of dog food from a site, but constantly gets recommended more dog kibble, that could be annoying or redundant. A recommender system that prompts other items — in this case, dog supplies like bowls and beds — could motivate a dog owner to add more things to their cart.

Technical Complexity: Given how ubiquitous recommender systems are, organizations need engineers who can understand and interpret the complex algorithms and maintain the parts as needed. You can learn the technical skills that go into creating and maintaining a recommender system with our path Build a Recommender System. If you’re new to coding, don’t sweat it — we’ll teach you Python and machine learning basics in this Codecademy path.

Why recommender systems can seem almost too good

Even though recommender systems are all around us, their effectiveness or accuracy can occasionally catch users off-guard. As a user, you might not realize how much data is being captured when you’re online shopping or using an app.

The way that developers can measure a user’s preferences is by examining how they rate items. Sometimes ratings are very explicit, like giving a book 5 stars on your Goodreads app. But even subtle behaviors — like how many times we view a specific pair of shoes or how long we spend on a page — can be interpreted as an implicit endorsement of the item.

The challenging thing is that recommender systems aren’t an exact science, because our preferences, interests, and internet behaviors may change over time, Nitya says. There’s a “mutually reinforcing feedback loop” between a user and the machine that creates a constant puzzle for developers to tackle, she says.

In the path Build a Recommender System, we’ll demystify the different types of data that’s used in a recommender system, and teach you to create a mathematical model that determines a user’s preferences.

The bottom line

“There’s no such thing as a ‘good’ algorithm or a ‘bad’ algorithm ultimately,” Nitya says. “A lot of it has to do with how cleverly it is applied and how much thought is there behind the design of it.” In other words, while machines can do their best to figure out what someone wants, it’s up to humans to make a decision and contextualize their options.

Of course, shopping for dog food is a relatively trivial example of recommender systems in our daily lives, but it’s important to note that there can be a “dark side” of recommender systems. Recommender systems are both sociological and technical puzzles, according to Nitya. In some cases, recommender systems that constantly “reward” users for certain problematic behaviors can exacerbate polarization, addictive behavior (like incessant scrolling), alienation, and powerlessness, she explains.

Throughout the process of building a recommender system, Nitya suggests keeping these questions in mind: What user behavior is being rewarded here, and is it enhancing or diminishing the user’s quality of life? Are there consequences of scaling this recommender system that might cause harm down the line? In our courses, you’ll learn how to take these questions into consideration when building recommender systems, and be able to identify a “successful” one.

Ready to learn more about this fascinating machine learning application? Check out the beginner-friendly path Build a Recommender System to learn how to use the programming language Python to create a recommender system from scratch. If you already have experience with Python and Pandas, you might want to start with the free intermediate course Learn Recommender Systems.  
Be sure to check out Codecademy’s full catalog of machine learning and data science courses to learn more about the technology that you use every day.

Machine Learning Courses & Tutorials | Codecademy

Machine Learning is an increasingly hot field of data science dedicated to enabling computers to learn from data. From spam filtering in social networks to computer vision for self-driving cars, the potential applications of Machine Learning are vast.

Most of us have experienced the uncanny accuracy of recommender systems before. For example, you were online shopping for a new keyboard one day, and then haunted by ads for other keyboards on your Instagram feed for weeks. Perhaps you liked a funny TikTok of a pig, and now your For You Page is all farm animal content. Or maybe you binge-watched Love Is Blind and Netflix won’t stop suggesting other reality dating shows.

The technology that helps guide individuals towards products is a machine learning algorithm called a “recommender system.” From the way we shop, to how we get our news, and even how we meet people, recommender systems are practically ubiquitous in our lives.

“We live in an attention economy, where there’s an overwhelming number of things, and recommender systems help us make decisions,” says ​​Nitya Mandyam, Senior Curriculum Developer at Codecademy. “It’s impossible to think of buying a shoe or a dress without having some kind of recommender system on the side giving you suggestions.”

In the new Codecademy path Build a Recommender System, you’ll get to look under the hood at how applications really get to know you, how these algorithms pinpoint options relevant to a user’s personal taste, and what it takes to code a successful recommender system. Here’s what you need to know about recommender systems, and how to start learning today.

What is a recommender system?

Recommender systems are algorithms that make recommendations to users about the best option to choose from a set of options. Of course, the “best” option is going to vary from person to person, which is why recommender systems turn to data about products and users’ preferences to generate individualized suggestions.

Unlike supervised machine learning models, which will predict an exact answer to a question or problem, recommender systems are preference-based, Nitya says. “A recommender system is a combination of human and machine interaction that decides whether something is good or a bad outcome,” she adds.

What are recommender systems used for?

Recommender systems are ideal for situations where users have a lot of options to choose from — like deciding which show to stream on Netflix, or wading through the sea of products on Amazon. Online dating apps use recommender systems to match people with a potential romantic partner based on similar factors, like their location and hobbies. Even social media platforms use recommender systems to determine what shows up in your feed.

Recommender systems are so ingrained in our lives that we’ve come to expect these tailored suggestions and recommendations from the technology we use. As a developer, it’s important to realize that users want systems that capture their tastes or interests — otherwise they might stop using it, Nitya says.

Tons of businesses rely on recommender systems to keep customers engaged with their product and earn more money. In ecommerce, for example, recommender systems can point customers to products that they’re more inclined to buy based on their past behaviors and purchases. Businesses can also learn a lot about their customers based on this data, and use it to inform other decisions.

How do you build a recommender system?

Creating a recommender system requires a combo of data science, software engineering, infrastructure, product, and design skills. The general-purpose programming language Python is used to create recommender systems. You’ll also need to use a little bit of algebra for recommender systems, but don’t be intimidated — the math involved is relatively easy to understand, Nitya says. In the path Build a Recommender System, we’ll walk you through the Python, machine learning, and basic math concepts necessary to make a recommender system.

There are a few types of recommender system techniques that take different approaches to finding that “best” option for a user. In the path Build a Recommender System and the free course Learn Recommender Systems, we’ll focus on collaborative filtering, which is a method that generates recommendations based on ratings information from similar users. With collaborative filtering, the idea is that people who have similar ratings for items tend to have similar tastes.

How will learning recommender systems help my career?

As more and more companies start using recommender systems in their businesses, organizations will need to hire people who have both domain expertise and technical know-how.

For people interested in data science and machine learning, recommender systems are just plain cool because they allow you to apply technical skills to a non-technical problem, like shoe shopping or streaming television shows, Nitya says. “You can apply data science and machine learning skills to quantify something that is seemingly unquantifiable, and get really good results,” she says. If you’re hoping to have a career in machine learning, recommender systems are a valuable skill that employers are looking for in job candidates.

And for folks who are interested in other areas of programming, recommender systems are a really good gateway into data science and machine learning, Nitya says. The path Build a Recommender System will teach you everything you need to know, even if you’re a beginner. “You don’t need to know that much, and we’re going to hold your hand from beginning to end in terms of how to build a system,” she adds.

Get started with recommender systems

Want to learn the technical skills needed to build a recommender system? You can jump in with our beginner-friendly path Build a Recommender System, where you’ll learn how to use Python, get introduced to basic machine-learning models, and put your knowledge to the test coding a recommender system.

If you’re already familiar with Python and Pandas, you might want to consider the intermediate course Learn Recommender Systems. In this free course, you’ll learn how to use a Python library called Surprise to create a recommender system for books. Surprise (short for “Simple Python Recommendation System Engine”) is an extension of the numerical computation library SciPy, and has built-in modules that are designed specifically for recommender systems.

Recommender systems are just one example of how machine learning touches our daily lives and decisions. To learn more about the exciting computer science specialty, check out all of Codecademy’s machine learning courses. A great place to start if you know Python but are new to machine learning is the course Learn the Basics of Machine Learning, or check out the path Get started with Machine Learning.

If your goal is to get a job in machine learning, you can dig deeper with the beginner-friendly career path Data Scientist: Machine Learning Specialist to learn more about what it takes to become a data-driven decision maker. And if you’ve never coded before but are inspired to start, try our popular course Learn Python 3.

Machine Learning Courses & Tutorials | Codecademy

Machine Learning is an increasingly hot field of data science dedicated to enabling computers to learn from data. From spam filtering in social networks to computer vision for self-driving cars, the potential applications of Machine Learning are vast.