The Fantastic Fixathon

Engineers at Pinterest are always focused on doing what’s best for the product, but working in a codebase that’s clean, well-maintained, and relatively bug-free transforms engineering tasks from being “just work” to enjoyable opportunities to flex our skills. We’re also enriched as engineers, both technically and otherwise, when we take…

Building interactive email with AMP

AMP (Accelerated Mobile Pages) is an open source technology created by Google to support fast mobile web pages. Over the years, we’ve partnered with Google and adopted AMP technology in our mobile web pages to deliver a faster, more efficient user experience. Most…

Building Pin stats

A few months back, we started building a way for businesses to create and showcase their latest and favorite content on their profiles. We also wanted to make it easier for businesses to understand how their Pins are performing. If a business can…

Simplifying web deploys

Over the past six months, Pinterest has moved to a CI/CD model for our API and web layers, which has truly improved agility by reducing time between merge and production. Prior to…

Pinterest + ktlint = ❤

Ha pasado casi un año desde que la base de código Android de Pinterest se convirtió en la prioridad de Kotlin, y aproximadamente dos años desde que adoptamos ktlint para el formato y lint de Kotlin. Hoy, compartimos que Pinterest se…

Pre-Submit Integration Tests For Ads-Serving

Introduction & Background The ads-serving platform is the highest-scale, highest-complexity, and highest-velocity recommendation service at Pinterest. Our ads business is growing and expanding, and the ads engineering team is iterating quickly to continue to improve the system. Therefore, it is vital to keep the system healthy, in order…

Setting Up Snowflake Secondary Roles with Tableau

At Pinterest, we heavily utilize Tableau for our enterprise analytics. In an effort to secure access of sensitive data to the appropriate business units, we moved the enterprise data into a Snowflake data warehouse. Using Snowflake as a data platform, we can create and manage…

Using machine learning to auto-organize boards

While planning one’s life might look different these days, our insights tell us people are saving ideas for the future more than ever. Last month, for instance, Pinterest had a 60% increase in the number…

PinSage: A new graph convolutional neural network for web-scale recommender systems

Deep learning methods have achieved unprecedented performance on a broad range of machine learning and artificial intelligence tasks like visual recognition, speech recognition and machine translation. However, despite amazing progress, deep learning research has mainly focused on data defined on Euclidean domains, such…

How we increased engagement using automatic personalized copy testing

Think about the last time you visited a website. Was there a word that helped draw you in? Now think about how that might be different if you spoke a different language, were a different age or grew up in a different part of…

Powering inclusive search & recommendations with our new visual skin tone model

To truly bring everyone the inspiration to create a life they love, Pinterest is committed to content diversity and to developing inclusive search and recommendation engines…

Partitioning Pinlater for Fun(?) and Profit(!)

Contained within the November 2015 announcement of the open-sourcing of Pinlater, our asynchronous job execution system, was a description of some of the improvements that had been made to the system since the original 2014 blog post describing its creation. Notable among…

Using PID controllers to diversify content types on home feed

Every day millions of Pinners visit the home feed to find inspiration on Pinterest. As a member of the home feed ranking team, it’s my job to not only figure out what relevant pins to show Pinners but also to make sure that…

How we use AutoML, Multi-task learning and Multi-tower models for Pinterest Ads

People come to Pinterest in an exploration mindset, often engaging with ads the same way they do with organic Pins. Within ads our mission is to help Pinners go from inspiration to action by introducing them to the compelling products and services that…

Contextual relevance in ads ranking

Pinterest runs an ads marketplace that balances value for Pinners, partners, and the business. We initially used engagement prediction as our main method to balance the marketplace before eventually adding contextual relevance to increase Pinner value. We have three main surfaces for determining…

HierTCN: Deep learning models for dynamic recommendations and inferring user interests

As we build a visual discovery engine, it’s crucial to understand user intent and serve relevant content through recommender systems that constantly learn from a cross-section of data to dynamically predict the next idea a Pinner will love. However, we found…

PinalyticsDB: A Time Series Database on top of Hbase

PinalyticsDB is Pinterest’s proprietary time series database. At Pinterest, we rely on PinalyticsDB as a backend for storing and visualizing thousands of time series reports such as the sample case below, segmented by country. PinalyticsDB was built several years ago on…

Pinterest + ktlint = ❤

It’s been nearly a year since Pinterest’s Android codebase became Kotlin-first, and about two years since we adopted ktlint for Kotlin linting and formatting. Today, we’re sharing that Pinterest has officially taken ownership over the project. Initially, we chose ktlint because of its…

How we built rearranging Pins

Listening to user feedback is essential to building a product Pinners love and use to discover and save ideas every day. Often, their feature requests present interesting technical challenges for our engineers. For example, today we launched the ability to…

Keeping Related Pins fresh

If you’ve ever heard someone mention “the Pinterest Rabbit Hole,” they’re likely referring to Related Pins, the ideas you see below a Pin you’ve tapped. Related Pins is a feed of content relevant to the closeup Pin and accounts for 40 percent of engagement…

API Profiling at Pinterest

When I walked into Pinterest on the first day of my internship and learned I’d be focusing on profiling the API Gateway service — the core backend service of the Pinterest product — my only thought was “What is profiling?”. Profiling is often shoved aside…

How Pinterest fights misinformation, hate speech, and self-harm content with machine learning

Pinterest is an inspiration network where people come for positivity and new ideas, and there’s nothing inspiring about harmful content. As a visual discovery engine with hundreds of billions of Pins…

Multi-task Learning and Calibration for Utility-based Home Feed Ranking

Home feed is one of the most important surfaces at Pinterest that drives a significant portion of engagement from the more than 400+ million people who visit each month. From a…

How Pinterest Fights Spam Using Machine Learning

Hundreds of millions of people regularly visit Pinterest to visually discover inspiring ideas among billions of Pins. Inspiration is a high bar and we must be vigilant in ensuring that Pinners don’t see spam, harmful content or misinformation. To enforce our…

The evolution of search at Pinterest

When Pinterest first launched it provided a new way for people to collect and organize ideas from around the web. What started as a place to save though, quickly became a unique service for discovery where Pinners could draw inspiration from each other, brands and…