Maritime transportation is critical for the global economy, with about 90% of goods traded by sea and volumes expected to triple by 2050. Despite rising demand, 40% to 50% of total miles are sailed empty (known as ballasting), causing significant economic and environmental costs. The oil transportation market is an ideal setting to study causes and remedies of ballasting, because: (i) oil tankers only carry a single cargo from origin to destination; and (ii) the market is highly fragmented.

Learning algorithms are proliferating in a variety of business contexts, ranging from automated bidding in online auctions to pricing on shopping platforms and setting rents. This diffusion has been accompanied by fears that such automation could facilitate collusion. A number of recent papers on algorithmic pricing show in simulations that learning algorithms coordinate on less-than-competitive outcomes.