Author Archives for Sift

Jun Qian and Machine Learning in the Real World

January 8, 2019 12:01 pm Published by Comments Off on 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 types […]


Deep Learning for Fraud Detection

March 22, 2018 10:18 am Published by Comments Off on Deep Learning for Fraud Detection

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


How Sift Trains Thousands of Models using Apache Airflow

March 20, 2018 12:25 pm Published by Comments Off on 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 do […]


Preloading your Javascript Split Files

February 28, 2018 8:34 am Published by Comments Off on 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 code […]


Building high-performance tracking SDKs for iOS

March 13, 2017 12:14 pm Published by Comments Off on 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 fraud […]


conf.startup.ml

January 13, 2017 2:16 pm Published by Comments Off on 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 we […]


The Engineering Team

September 27, 2016 5:25 pm Published by 1 Comment

We started Sift Science over 5 years ago with the mission to improve outcomes with data and create a safe, […]


Browser DGAF (that you use React)

March 16, 2016 5:58 pm Published by Comments Off on 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 echoed the issues and solutions that I’ve been working through on the Sift Science Console. So I was inspired to chime in with some of my own React performance debugging experiences in what may become a short series itself.


The Sass Mixins/Placeholders I Can’t Live Without for Responsive Web Design

July 24, 2015 4:50 pm Published by Comments Off on The Sass Mixins/Placeholders I Can’t Live Without for Responsive Web Design

Here at Sift Science, we just completed another big step in our ongoing marketing site redesign, overhauling the homepage and replacing old landing pages with [prettier, responsive, and more performant ones][1]. While the big performance improvements aren't quite ready to showcase yet (check in soon for more on that), I realized that there are a few custom Sass mixins and placeholders that I rely on heavily for responsive development—I'm not actually sure what I'd do without them—and I thought I'd share them here along with some CodePens so that other people might also take advantage of them!


How We Rebuilt Our App, Part 2: From Rails + Marionette to React

June 9, 2015 6:32 pm Published by 2 Comments

In the first post of this series, we gave an overview of Sift Science’s architectural migration to React and Dropwizard. We followed up with some best practices for scaling React in a production setting and some tips on using React with D3. Today’s post will chronicle the front-end migration process of moving from Rails + Backbone + Marionette + Handlebars to a static Backbone + React console, and the challenges we encountered.


d-Threeact: How the Sift Science Console Team Made d3 and React the Best of Friends

May 19, 2015 10:25 pm Published by 13 Comments

A little less than a year ago, the Sift Science Console Team decided to migrate its Backbone and Marionette Views to ReactJS see also our post on specific React tips we learned along the way.  Among the many facets of a piece-by-piece migration like this was figuring out how best to manage (err...'reactify') our d3 charts. There were already a couple good reads/ listens on this topic—with very different views on the responsibilities of each library—which we found quite helpful in establishing our own approach.


How we rebuilt our app on React and Dropwizard, Part 1

April 28, 2015 8:06 pm Published by Comments Off on How we rebuilt our app on React and Dropwizard, Part 1

Two years ago, we publicly launched our first fraud product with the goal of making it easy for anybody to leverage the same machine learning technology that protects the largest internet retailers. That product had a very simple interface: we provided one API for sending data about user behavior and another to query the fraud score of a user. But as our customer base grew, we needed better internal tools to debug and surface customer issues.