Recommender Systems

How we provide inspired suggestions for travelers — Lucy (Jingyu) Zou, Eric Song Background At Expedia Group™, we aim to provide high-quality recommendations for travel to encourage bookings and inspire exploration. Traditionally, recommendation models have been evaluated by comparing relevance and ranking metrics, i.e., NDCG (Normalized Discounted Cumulative Gain), precision. And while being accurate is important, users prefer having…

In today’s world of endless choices, we often rely on recommendations from others to help us make decisions. This is where Recommender Systems come in — they help us discover products, services, and content that we might not have found otherwise. …

Recommender systems have become increasingly important in recent years, as more and more businesses have come to rely on them to help users discover new products and services that they might be interested in. …

— Luke Thorburn, Jonathan Stray, Priyanjana Bengani The term “amplification” is ubiquitous in discussions of recommender systems and even legislation, but is not well-defined. We have previously argued that the term is too ambiguous to be used in law, and that the three most common interpretations — comparison with a…

In the next few write-ups, we’ll explore the often overlooked superpower of modern-day recommender systems: naive models. The Simplest Learning Algorithm In high school, you might have encountered intriguing probability puzzles, such as the Monty-Hall problem, which involved manipulating conditional probabilities. But at its core, Bayes’ formula is quite intuitive: Do you hold a…

I’m a runner. I live in Chicago, so we get all four seasons, sometimes within the span of one week. I hate the treadmill, and prefer to run outside as much as possible. Yes, that is me above, running a 5K race when it was 3°F. Every winter, I seem…

Basic recommenders that are easy to understand and implement, as well as fast to train — Recommender systems are algorithms designed to provide user recommendations based on their past behavior, preferences, and interactions. Becoming integral to various industries, including e-commerce, entertainment, and advertising, recommender systems improve user experience, increase customer retention, and drive sales.

YouTube, Netflix, Spotify or even Facebook and any other entertainment-consume applications uses the same thing (formula) to provide enormous content to your feed, so you can stay relax on your phone and not even bother to leave your bed. This thing is called recommender system. What the heck is recommender system? Every single random video, films…

In this lesson, we’ll focus on content-based filtering, another common technique for building recommender systems. We’ll build intuition around the key concepts and steps involved in content-based filtering. Intuition: Content-based filtering is based on the idea that users will be interested in items that are similar to those they’ve liked…