Presented By O’Reilly and Intel AI
Put AI to work
8-9 Oct 2018: Training
9-11 Oct 2018: Tutorials & Conference
London, UK

How AI is taking geospatial data from alternative to mainstream in finance

James Crawford (Orbital Insight)
14:35–15:15 Wednesday, 10 October 2018
Secondary topics:  Financial Services, Retail and e-commerce

Who is this presentation for?

  • Technology officers at financial institutions, data analysts, and computer vision engineers

Prerequisite knowledge

  • A basic understanding of financial markets and geospatial analytics (useful but not required)

What you'll learn

  • Learn how artificial intelligence, specifically computer vision and deep learning, is uniquely suited to analyze satellite imagery and other geospatial data at scale in order to track the changes in patterns that reveal socioeconomic trends happening on the ground

Description

The global financial industry is in flux. Information that was once unattainable has become commonplace, and data that was once “alternative” is quickly becoming mainstream due to advances in artificial intelligence, cloud computing, and other technologies. No area exemplifies this trend better than geospatial analytics.

In the last five years, an explosion in the number of commercial satellites means that we have much more frequent imagery of more of the planet than ever before in history, which is useful for people trying to better understand what’s happening at ports, mines, and factories as well as measuring other economic indicators—more images means more accurate, timely understanding. However, to fully take advantage of the petabytes of satellite data available, we must turn to artificial intelligence to assist with the analysis. There simply aren’t enough human analysts to do the job efficiently.

James Crawford explains how artificial intelligence can be used to analyze geospatial datasets at scale to detect patterns of socioeconomic change, which finance professional leverage to make more informed decisions. Jimi offers an overview of the types of artificial intelligence used to interpret geospatial data and walks you through two use cases. The first is an example pulled from retail analysis, showing how using artificial intelligence to count cars in all of a retailer’s parking lots across a country can be a good proxy for sales—one that’s available before official earnings. For instance, Orbital Insight found that J.C. Penney car counts were down 5% year over year in Q4 of 2016, which mirrored in-store sales, which were down 0.7% in the same period. The second illustrates how artificial intelligence can be used to estimate fill levels in floating roof oil tanks, providing insight into a country’s overall oil storage even when official statistics are unavailable.

Photo of James Crawford

James Crawford

Orbital Insight

James Crawford is the founder and CEO of Orbital Insight, where he leads the company’s efforts to leverage artificial intelligence to create geospatial analytics for an interconnected world. Previously, Jimi was the SVP of science and engineering at the Climate Corporation; CTO and software architect at Moon Express, whose goal was putting the first commercial robot on the moon; and engineering director for Google Book Search, where he was in charge of Google’s project to scan, index, and make searchable all the world’s books. He has also spent time at the NASA Ames Research Center, leading autonomy and robotics projects. He has authored over 15 peer-reviewed publications, resulting in five patents. Jimi holds both a PhD and master’s degree in computer science from the University of Texas at Austin and a BA in math and computer science from Rice University.