Multi-Domain Fraud Detection While Reducing Good User Declines — Part II

Multi-Domain Fraud Detection While Reducing Good User Declines — Part IIIn part I of this two-part series, we outlined the approaches for multi-domain fraud detection while also optimizing for feature stability in post-deployment scenarios. This post will demonstrate approaches to reduce decline of good users, incrementally, on the top of the existing model architectu...

Multi-Domain Fraud Detection While Reducing Good User Declines — Part I

Multi-Domain Fraud Detection While Reducing Good User Declines — Part ILearning Fraud Patterns Using Multi-task Deep Learning Methods while approving good customers swiftlyPhoto by Fabio Traina on UnsplashThis post is the first in a series of two blog posts that outline the approach towards multi-domain fraud detection while optimizing for fraud catch rate across diff...

Learning with Limited Labeled Data for Natural Language Understanding

IntroductionSupervised machine learning models need large amounts of labeled data. The more data you use to train your model, the better it performs. With the advent of deep learning-based models, the demand for data has increased by orders of magnitude. State-of-the-art deep learning NLP (Natural Language Processing) models typically have several hundred million para...

A Look Behind Blend: The Personalized Playlist for You…and You

What does it take to go from an idea for a new playlist, to shipping that playlist to Spotify users all around the world? From inception, to prototyping, to QAing, and finally shipping, releasing a new playlist at Spotify is a long process full of new learnings every time.  We recently launched a new playlist ......

Using Documentation-Driven Design to Guide API Decisions

Image of a person writing and working on a computer by Danai via AdobeAs software design evolves, so do the thought processes behind the design decisions we make as engineers. Some of these development practices are widely known and talked about, such as Test-Driven Design, where changes to code are made in programmatic tests before they’re implemented in actual busin...

Measuring Web Performance at Airbnb

Learn what web performance metrics Airbnb tracks, how we measure them, and how we consider tradeoffs between them in practice.Josh NelsonHow long did it take for this web page to load? It’s a common question industrywide, but is it the right one? Recently, there has been a shift from using single seconds-based metrics like “page load”, to metrics that paint a more hol...

The Staging Dichotomy: Part One

A two-part series on how eBay turned around an impeding staging environment into its biggest asset for developer productivity....

How Pinterest powers a healthy comment ecosystem with machine learning

Yuanfang Song | Machine Learning Engineer, Trust and Safety; Qinglong Zeng | Engineering Manager, Content Quality Signals; and Vishwakarma Singh | Machine Learning Lead, Trust and SafetyAs Pinterest continues to evolve from a place to just save ideas to a platform for discovering content that inspires action, there’s been an increase in native content from creators pu...

Building Data Quality into the Enterprise Data Lake

Photo by metamorworks on ShutterstockThis article describes how an Enterprise Data Lake team (EDL) at PayPal built the Rule Execution Framework (REF) to address an enterprise-level opportunity: creating a centralized, enterprise-level generic rule configuration system for defining, managing, controlling, and deploying the data quality framework’s rules and rulesets.Wh...

How Spotify Uses ML to Create the Future of Personalization

Machine learning is what drives personalization on Spotify. We may have a single platform with 381 million different users, but it may actually be more accurate to say there are 381 million individual versions of Spotify, each one filled with different Home pages, playlists, and recommendations. But with a library of over 70 million tracks ......