Computing Global Strategies for Multi-Market Commodity Trading

Thefocus of this workis the computationof efficient strategies for commoditytrading in a multi-marketenvironment. In today's "global economy"commodities are often boughtin one location and then sold (right away,or after somestorage period) in different markets. Thus, a trading decision in one location must be based on expectations about future price curves in all other relevant markets, and on current and future storage and transportation costs. Investors try to compute a strategy that maximizesexpected return, usually with somelimitations on assumedrisk. With standard stochastic assumptions on commodity price fluctuations, computingan optimal strategy can be modeledas a Markovdecision process (MDP). However,in general such a formulation does not lead to efficient algorithms. In this workwepropose a modelfor representing the multi-market trading problem and showhowto obtain efficient structured algorithms for computingoptimalstrategies for a numberof commonlyused tradin...

• Type: Conference
• Year: 2000
• Where: AIPS
• Authors: Milos Hauskrecht, Luis E. Ortiz, Ioannis Tsochantaridis, Eli Upfal
• Keywords: AIPS 2000, Artificial Intelligence, Computationof Efficient Strategies, Efficient Structured Algorithms, Future Price Curves