Four lessons in making Pinterest faster on Android

As engineers, we intuitively know that a faster app is a better experience for Pinners, but we also have proof that when web pages load faster, user growth improves. Last year, we doubled down on performance across our platforms so…

Introducing Pinqueue3.0, Pinterest’s next-gen content moderation platform

In 2016, we reached a milestone of launching Pinqueue2.0, which has since become the go-to content moderation tool for the engineering, community, and data science teams. One of our top priorities at Pinterest is fostering a safe and trustworthy experience for all…

Calidad y pruebas de las métricas publicitarias en dispositivos móviles

En Pinterest, todos los días ayudamos a nuestros socios de publicidad a llegar a los usuarios a través de diferentes formatos de anuncios y les ofrecemos métricas y análisis sobre el rendimiento de sus anuncios. Mantener la confianza…

Building a universal search system for Pinterest

On Pinterest, the best answer goes beyond text, but can even go beyond an image too. When you’re looking for eye makeup ideas for example, a video personalized to your skin tone range teaching you how to create a certain look is likely…

Open sourcing Querybook, Pinterest’s collaborative big data hub

Charlie Gu | Tech Lead, Analytics Platform, Lena Ryoo | Software Engineer, Analytics Platform, and Justin Mejorada-Pier | Engineering Manager, Analytics Platform With more than 300 billion Pins, Pinterest is powering an ever-growing and unique dataset that maps interests, ideas…

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…

Using Kafka to throttle QPS on MySQL shards in bulk write APIs

At Pinterest, backend core services are in charge of various operations on pins, boards, and users from both Pinners and internal services. While Pinners’ operations are identified as online traffic because of real-time response, internal traffic is identified as offline because processing is…

Pinterest Flink Deployment Framework

Background At Pinterest, stream processing allows us to unlock value from real time data for pinners and partners. The Stream Processing Platform team is working on building a reliable and scalable platform to support many critical streaming applications including real-time experiment analytics…

Using graph algorithms to optimize Kafka operations, Part 1

Pinterest uses Kafka across the board for data movement. The Logging Platform team alone manages over 3,000 Kafka brokers transporting trillions of messages per day to help bring more than 320 million monthly active Pinners the inspiration to create a life they love. …

How we designed our Continuous Integration System to be more than 50% Faster

Earlier this year, the Engineering Productivity team at Pinterest published a blog called How a one line change decreased our clone times by 99%. In that post, we described how a simple Git configuration sped up clone times in one of our…

Powering Pinterest ads analytics with Apache Druid

The Change When we launched Promoted Pins in 2014, we chose Apache HBase as our database to store and serve all of our reporting metrics. At the beginning of our ads business, this was an appropriate choice because…

What it’s like to interview at Pinterest

Interviews have traditionally been thought of as an unpleasant but necessary experience. Candidates often find them stressful and many come in having had poor interview experiences in the past. However, interviews are the clearest opportunity for companies to articulate and demonstrate…

Empowering Pinterest data scientists and machine learning engineers with PySpark

Data scientists and machine learning engineers at Pinterest found themselves hitting major challenges with existing tools. Hive and Presto were readily accessible tools for large scale data transformations, but complex logic…

Detecting Image Similarity in (Near) Real-time Using Apache Flink

Pinterest is a visual platform at its core, so the need to understand and act on images is paramount. A couple of years ago, the Content Quality team designed and implemented our own batch pipeline to detect…

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…

Upgrading Pinterest operational metrics

Recently, Pinterest hit a major milestone: 300 million monthly active users around the world. To reliably serve this user base with our large content corpus, Pinterest’s engineering team maintains thousands of services all working together in tight…

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…

Improving data processing efficiency using partial deserialization of Thrift

At Pinterest we’ve worked to greatly improve data processing efficiency. One quote that resonates with our unique approach is from writer Antoine de Saint-Exupéry: “Perfection is achieved, not when there is nothing more to add, but when there is nothing left to take away.” Ultimately…

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…

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…

Seven best practices for inclusive product design

At Pinterest, our mission is to help you discover and do what you love. We’re building a product for everyone, because the best Pinterest is inclusive and easily usable for people with all levels of abilities. That’s why today we’re sharing our…

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…

Understanding the product cycle of discovery to purchase on Pinterest

Pinners have always used Pinterest for shopping, as they often come in a planning mindset and are exploring products and…

Pin2Interest: A scalable system for content classification

Content understanding is at the core of any great recommendation system. By knowing what each Pin is about, Pinterest can connect Pinners with the most relevant and inspiring content that best matches their interests. Taxonomy of interests The Interest Taxonomy captures popular concepts that appear within Pinterest…

What we learned from an iOS app OOMs incident

In early 2020, we started seeing significantly elevated out-of-memory (OOM) crashes in the Pinterest iOS app. That incident resulted in a declined Crash-Free Users Rate (CFUR), from the previous 99% to 96%, which was a steep drop. What was going on? We improved…