Commodity traders and hedge funds have long used physical commodity flows as a critical input to their pricing and risk models. New advances in data and analytics now enable traders to predict these flows even before they happen. Using a combination of public and proprietary data, machine learning techniques, custom models spanning multiple domains, and human-in-the-loop data collection and collation, it is now possible to predict commodity shipments two to three weeks in advance of published import-export figures.
Abraham Thomas demonstrates how maritime data can be used to predict physical commodity flows, in a case study that covers every stage of the data lifecycle, from raw data acquisition, data cleansing and structuring, and machine learning and probabilistic modeling to conversion to tractable format, packaging for final audience, and commercialization and distribution.
Abraham Thomas is the cofounder and chief data officer of Quandl, a company he and cofounder Tammer Kamel created with the goal of making it easy for anyone to find and use high-quality data effectively in their professional decision making. Previously, Abraham was a portfolio manager and head of US bond trading at Simplex Asset Management, a multi-billion-dollar hedge fund group with offices in Tokyo, Hong Kong, and Princeton. He holds a degree from IIT Bombay.
©2017, O'Reilly Media, Inc. • (800) 889-8969 or (707) 827-7019 • Monday-Friday 7:30am-5pm PT • All trademarks and registered trademarks appearing on oreilly.com are the property of their respective owners. • firstname.lastname@example.org