Optimization of Soybean Buying Strategies Using Derivatives

Abstract

The portfolio model of hedging framework, based off Markowitz (1952), is used to determine the best mix of futures, basis, and option contracts to hedge a soybean purchase from PNW 28 weeks in to the future. Eighteen options are incorporated including in-the-money, at-the-money, and out-of-the-money call and puts with different expiration dates. Futures and option pricing data is extracted from ProphetX from November of 2013 to December of 2016. Expected utility objectives including mean-variance, CVaR, Mean-CVaR, and Mean-CVaR with copula are maximized using linear programming optimization methods. A two stage model is built to simulate hedging scenarios while measuring various statistics. Under high risk aversion, a standard futures hedge performs the best. Buyers with lower risk aversion should explore option strategies. In-the-money calls, collars, strangles, and short butterfly strategies all perform well.