Jeremy Stanley

Sorting shopping lists at Instacart with deep learning using Keras and Tensorflow.

In this article, we've summarized the advice we give to founders who are interested in building data science teams. We explain why data science is so important for many startups, when companies should begin investing in it, where to put data science in their organization and how to build a culture where data science thrives.

Instacart is an e-commerce marketplace, a complex last-mile logistics engine, and a dynamic source of work for personal shoppers. Data science plays a key role in our success in each endeavor. This article covers the key challenges we are tackling with data science, how we've integrated data science into engineering, and the cultural traits we look for when building the team.

Why I joined Instacart - love the product, amazing data science challenges and a humble culture.

Data science leaders are seeking fundamentally better ways to evaluate talent. In this article, I describe a new process I adapted to hire great data science talent efficiently and confidently. I describe the limitations of existing hiring approaches, the key goals this process seeks to improve, the underlying principles it is based upon and then I walk through the implementation we have experimented with at Sailthru.

It takes skill to build a meaningful predictive model even with the abundance of implementations of modern machine learning algorithms and readily available computing resources. Building a model becomes challenging if hundreds of terabytes of data need to be processed to produce the training data set. In a digital advertising technology setting, we are faced with the need to build thousands of such models that predict user behavior and power advertising campaigns in a 24/7 chaotic real-time… Mehr zeigen

It takes skill to build a meaningful predictive model even with the abundance of implementations of modern machine learning algorithms and readily available computing resources. Building a model becomes challenging if hundreds of terabytes of data need to be processed to produce the training data set. In a digital advertising technology setting, we are faced with the need to build thousands of such models that predict user behavior and power advertising campaigns in a 24/7 chaotic real-time production environment. As data scientists, we also have to convince other internal departments critical to implementation success, our management, and our customers that our machine learning system works. In this paper, we present the details of the design and implementation of an automated, robust machine learning platform that impacts billions of advertising impressions monthly. This platform enables us to continuously optimize thousands of campaigns over hundreds of millions of users, on multiple continents, against varying performance objectives. Weniger anzeigen

Guidance on the selection of a viewability technology provider, and a summary of recommended applications of viewability data for both brand and direct response advertisers.

A summary of the six primary technologies used in measuring viewability today, along with strengths and weaknesses: page geometry, panel, behavioral proxy, browser exploits, publisher API and browser monitoring.