"Testing Efficiency of Commodity Markets Using Artificial Neural Networks"
Naveed Ahmad 2004
Abstract
This study uses feed-forward neural networks with a back-propagation learning algorithm to test the efficiency of the soybean futures commodity market. The soybean futures market was tested for the weak form of efficiency outlined by the Efficient Market Hypothesis first proposed by Fama (1970). The study found that the soybean futures market is efficient in the weak form since positive profits were not realized after applying a trading rule to the predictions from the neural network.