Originally published in DoorDash Engineering Feb 13, 2018. To A/B or not to A/B, that is the question Overview On the Dispatch team at DoorDash, we use simulation, empirical observation, and experimentation to make progress towards our goals; however, given the systemic nature of many of our products, simple A/B tests are often ineffective due
Originally published in Towards Data Science on Oct 26, 2020. This year, Twitter sponsored the RecSys 2020 Challenge, providing a large dataset of user engagements. In this post, we describe the challenge and the insights we had...
Multi-armed bandits have become a popular alternative to traditional A/B testing for online experimentation at Stitch Fix. We’ve recently decided to extend our experimentation platform to include multi-armed bandits as a first-class feature. This post gives an...
Originally published in Ars Technica, Aug 6, 2020. Apple AI chief and ex-Googler John Giannandrea dives into the details with Ars. Machine learning (ML) and artificial intelligence (AI) now permeate nearly every feature on the iPhone, but...
Originally published in a16z.com, Aug 12, 2020. AI has enormous potential to disrupt markets that have traditionally been out of reach for software. These markets – which have relied on humans to navigate natural language, images, and...
Originally published in Vox.com, July 31, 2020. How Facebook decides which ads to display on your News Feed. In 2019, Facebook settled a lawsuit with civil rights organizations following the revelation that advertisers could use the targeting...
