Monitoring global trade by products, using Big Data

This paper develops a novel methodology to derive timely, experimental estimates of trade by commodity with global coverage using messages from the Automatic Identification System (AIS). By transforming high-frequency vessel movements into trade proxies, the approach makes it possible to monitor global cross-border flows in near real time for 23 commodity groups worldwide, covering 97.8% of existing berths across 3534 ports. The methodology improves upon Pilgrim et al. (2024) by exploiting information at the berth level, which increases the accuracy of port delineation and allows, with the use of satellite imagery and a rule-based approach, to get a mapping of commodities. While the resulting trade estimates are experimental and not designed to replace official trade statistics and are surrounded by uncertainties, especially regarding containerised trade, they provide valuable and complementary information on trade dynamics, particularly in periods of heightened uncertainty or rapid change. Their main strength lies in their ability to capture turning points, disruptions and emerging trends well ahead of traditional data releases. The methodology also allows to derive timely estimates of transit trade.