Sift Engineering Blog

Building AI Products: Learnings from a Panel with Advancing Women in Product

Sift is passionate about education, collaboration, and empowering innovation. Last month, Sift partnered with Advancing Women in Product to...

Full blog post: Building AI Products: Learnings from a Panel with Advancing Women in Product

Culture

Sift’s 2023 hackathon spotlights our “Start with the customer” company value

One of our core values at Sift is “Start with the customer”— meaning we always start with solving real-world...

Full blog post: Sift’s 2023 hackathon spotlights our “Start with the customer” company value

Articles

Response Recommendations for Dispute Management

Introduction You may currently be working on a chargeback response, a representment, or a “pick-a-noun” content that you hope...

Full blog post: Response Recommendations for Dispute Management

Articles

Continuous ML Improvements @ Sift Scale

The SaaS and fraud space is dynamic and ever evolving. Customers, old and new, bring new fraud use cases...

Full blog post: Continuous ML Improvements @ Sift Scale

Articles

Text clusters: Fighting spam content using neural networks and unsupervised ML – Part 2

In the part 1 of this blog series, we discussed the data science behind our new text clustering feature,...

Full blog post: Text clusters: Fighting spam content using neural networks and unsupervised ML – Part 2

Articles

Text clusters – Fighting spam using neural networks and unsupervised ML – Part 1

The spam problem “Spam will be a thing of the past in two years’ time” – Bill Gates in...

Full blog post: Text clusters – Fighting spam using neural networks and unsupervised ML – Part 1

Culture

Sift’s 2021 Hackathon brings the entire company together for innovation

One of our values at Sift is “Ever Better”, meaning that we don’t settle for the status quo, and...

Full blog post: Sift’s 2021 Hackathon brings the entire company together for innovation

(Part 4/4)" style="background-image: url('https://engineering.sift.com/wp-content/uploads/2020/02/04_GCP_Migration_tile.jpg');">

Articles

Lessons Learned From Bigtable Data Migration
(Part 4/4)

In the previous article, we discussed how we evaluated Cloud Bigtable for Sift, how we prepared our systems for...

Full blog post: Lessons Learned From Bigtable Data Migration
(Part 4/4)

Articles

Watchtower: Automated Anomaly Detection at Scale

As the leader in Digital Trust & Safety and a pioneer in using machine learning to fight fraud, we...

Full blog post: Watchtower: Automated Anomaly Detection at Scale

(Part 3/4)" style="background-image: url('https://engineering.sift.com/wp-content/uploads/2020/02/03_GCP_Migration_tile.jpg');">

Articles

Planning a Zero Downtime Data Migration
(Part 3/4)

In the previous article, we described how we assessed the fitness of Bigtable to Sift’s use cases. The proof...

Full blog post: Planning a Zero Downtime Data Migration
(Part 3/4)

(Part 2/4)" style="background-image: url('https://engineering.sift.com/wp-content/uploads/2020/02/02_GCP_Migration_tile.jpg');">

Articles

Evaluating Cloud Bigtable
(Part 2/4)

In the previous article, we presented the challenges that prompted us to migrate away from HBase on Amazon Web...

Full blog post: Evaluating Cloud Bigtable
(Part 2/4)

(Part 1/4)" style="background-image: url('https://engineering.sift.com/wp-content/uploads/2020/02/01_GCP_Migration_tile.jpg');">

Articles

Migrating our cloud infrastructure to Google Cloud
(Part 1/4)

At Sift, we have built a scalable and highly available technology platform to enhance trust and safety in the...

Full blog post: Migrating our cloud infrastructure to Google Cloud
(Part 1/4)

Articles

Introducing Resourcerer: Declarative React Data-Fetching for REST APIs

We are excited to announce the public release of a package we’ve been using internally at Sift to handle...

Full blog post: Introducing Resourcerer: Declarative React Data-Fetching for REST APIs

Culture

Sift Named On Built In’s “Best Places to Work” Award List

Sift is excited to announce that we’ve been named one of Built In Seattle’s 2019 Best Places to Work!...

Full blog post: Sift Named On Built In’s “Best Places to Work” Award List

Culture

Jun Qian and Machine Learning in the Real World

Jun Qian’s typical day consists of thinking through real-world machine learning applications, hiring brilliant engineers, and digging through incomparable...

Full blog post: Jun Qian and Machine Learning in the Real World

Articles

Security Bulletin – AWS Reported AMI Issue

AWS notified Sift on September 18th, 2018, of an issue where AWS incorrectly labeled Amazon Machine Images associated with...

Full blog post: Security Bulletin – AWS Reported AMI Issue

Culture

Sift Engineering Holds Spring Hackathon

This spring, Sift Science Engineering completed another one-week hackathon. Sift has a long tradition of hackathons and many hackathon...

Full blog post: Sift Engineering Holds Spring Hackathon

Articles

Engineering Management – Effective Design Reviews

Engineering Management Series The past few years have been a time of incredible growth at Sift and there is...

Full blog post: Engineering Management – Effective Design Reviews

Articles

The Sift Science Console’s Javascript Loading Strategy

A few years ago, the advice for keeping your page fast was to keep your page weight down. These...

Full blog post: The Sift Science Console’s Javascript Loading Strategy

Articles

Testing and Deploying Sift’s JavaScript SDK

The rapidly evolving device and browser landscape allows us to collect increasingly rich data via our snippet. Because we...

Full blog post: Testing and Deploying Sift’s JavaScript SDK

Articles

Does Your Model Launch Have a SafetyNet?

In the adversarial and constantly changing world of fraud detection and trust enablement, keeping up with the most recent...

Full blog post: Does Your Model Launch Have a SafetyNet?

Articles

Deep Learning for Fraud Detection

In this blog post we detail how Sift has begun leveraging deep learning (in the form of RNNs) to...

Full blog post: Deep Learning for Fraud Detection

Articles

How Sift Trains Thousands of Models using Apache Airflow

At Sift Science, engineers train large machine learning models for thousands of customers. We need processes and tools to...

Full blog post: How Sift Trains Thousands of Models using Apache Airflow

Articles

Preloading your Javascript Split Files

By now, you’re probably familiar with the benefits of splitting up your app’s javascript into several smaller files through...

Full blog post: Preloading your Javascript Split Files

Culture

2017 Sift Engineering in Review

2017 has been a pivotal year for Sift Science and the engineering team. We’ve delivered on amazing product launches,...

Full blog post: 2017 Sift Engineering in Review

Articles

Models in Disguise: How Sift Science Ships Non-Disruptive Model Changes

TL;DR: We can transform the score distributions of new models to match those of old models, while preserving the...

Full blog post: Models in Disguise: How Sift Science Ships Non-Disruptive Model Changes

Talks

Seattle Office Holds First Public Event: Custom Machine Learning Models at Scale

On April 19, 2017 the newly-opened Seattle Sift Science Research and Development Office hosted its first public speaking event: Alex...

Full blog post: Seattle Office Holds First Public Event: Custom Machine Learning Models at Scale

Articles

Building high-performance tracking SDKs for iOS

Sift Science’s iOS SDK enables mobile applications to send us device properties and application lifecycle events for use in...

Full blog post: Building high-performance tracking SDKs for iOS

Talks

Druid at Sift

At Sift Science, we protect online businesses from fraud and abuse. We do this by processing lots of data...

Full blog post: Druid at Sift

Articles

How Workflows Work: Reliable Workflow Processing at Scale

This summer we launched Workflows, a new product that allows fraud managers to build and update their fraud processes...

Full blog post: How Workflows Work: Reliable Workflow Processing at Scale

Talks

conf.startup.ml

We’re very proud to sponsor Startup ML’s conference on Putting Deep Learning into Production, being held Jan 21, 2017. While...

Full blog post: conf.startup.ml

Articles

ML Experiments at Sift Science, Pt. 3: Building the Right Tools

In the first two posts of this three-part series we discussed how we ensure correctness when conducting and analyzing...

Full blog post: ML Experiments at Sift Science, Pt. 3: Building the Right Tools

Articles

ML Experiments at Sift Science, Pt. 2: Analyzing Thousands of Models

In the first post on ML Experiments at Sift Science, we described how we minimize bias in our offline...

Full blog post: ML Experiments at Sift Science, Pt. 2: Analyzing Thousands of Models

Articles

ML Experiments at Sift Science, Part 1: Minimizing Bias

At Sift Science we use machine learning to prevent various forms of abuse on the internet. To do this,...

Full blog post: ML Experiments at Sift Science, Part 1: Minimizing Bias

Articles

Improving Perceived SPA Performance by Prefetching Critical Resources

I remember being intrigued by Smashing Magazine’s post this summer about using PJAX to effectively turn static markup websites...

Full blog post: Improving Perceived SPA Performance by Prefetching Critical Resources

Culture

The Engineering Team

We started Sift Science over 5 years ago with the mission to improve outcomes with data and create a...

Full blog post: The Engineering Team

Articles

Browser DGAF (that you use React) Pt. 2: FLIPping in React

In the first post in this series, we looked at how coding within the React paradigm could lead to...

Full blog post: Browser DGAF (that you use React) Pt. 2: FLIPping in React

Articles

Open Source: Kafka Partition Reassignment with Minimal Data Movement

We’re happy to announce that we’re open sourcing one component of our Kafka operations toolkit: an algorithm that computes...

Full blog post: Open Source: Kafka Partition Reassignment with Minimal Data Movement

Articles

Concurrency and At Least Once Semantics with the New Kafka Consumer

This post is the first in a series that describes our experience in adopting Apache Kafka. Here at Sift...

Full blog post: Concurrency and At Least Once Semantics with the New Kafka Consumer

Articles

Browser DGAF (that you use React)

Adventures in React Performance DebuggingRecently I read Benchling’s 2-part series in debugging performance issues in React, and it really...

Full blog post: Browser DGAF (that you use React)

Sift Engineering Blog

Building AI Products: Learnings from a Panel with Advancing Women in Product

Sift’s 2023 hackathon spotlights our “Start with the customer” company value

Response Recommendations for Dispute Management

Continuous ML Improvements @ Sift Scale

Text clusters: Fighting spam content using neural networks and unsupervised ML – Part 2

Text clusters – Fighting spam using neural networks and unsupervised ML – Part 1

Sift’s 2021 Hackathon brings the entire company together for innovation

Lessons Learned From Bigtable Data Migration(Part 4/4)

Watchtower: Automated Anomaly Detection at Scale

Planning a Zero Downtime Data Migration (Part 3/4)

Evaluating Cloud Bigtable (Part 2/4)

Migrating our cloud infrastructure to Google Cloud (Part 1/4)

Introducing Resourcerer: Declarative React Data-Fetching for REST APIs

Sift Named On Built In’s “Best Places to Work” Award List

Jun Qian and Machine Learning in the Real World

Security Bulletin – AWS Reported AMI Issue

Sift Engineering Holds Spring Hackathon

Engineering Management – Effective Design Reviews

The Sift Science Console’s Javascript Loading Strategy

Testing and Deploying Sift’s JavaScript SDK

Does Your Model Launch Have a SafetyNet?

Deep Learning for Fraud Detection

How Sift Trains Thousands of Models using Apache Airflow

Preloading your Javascript Split Files

2017 Sift Engineering in Review

Models in Disguise: How Sift Science Ships Non-Disruptive Model Changes

Seattle Office Holds First Public Event: Custom Machine Learning Models at Scale

Building high-performance tracking SDKs for iOS

Druid at Sift

How Workflows Work: Reliable Workflow Processing at Scale

conf.startup.ml

ML Experiments at Sift Science, Pt. 3: Building the Right Tools

ML Experiments at Sift Science, Pt. 2: Analyzing Thousands of Models

ML Experiments at Sift Science, Part 1: Minimizing Bias

Improving Perceived SPA Performance by Prefetching Critical Resources

The Engineering Team

Browser DGAF (that you use React) Pt. 2: FLIPping in React

Open Source: Kafka Partition Reassignment with Minimal Data Movement

Concurrency and At Least Once Semantics with the New Kafka Consumer

Browser DGAF (that you use React)

Lessons Learned From Bigtable Data Migration
(Part 4/4)

Planning a Zero Downtime Data Migration
(Part 3/4)

Evaluating Cloud Bigtable
(Part 2/4)

Migrating our cloud infrastructure to Google Cloud
(Part 1/4)