Intermarket divergence — A robust method for generating robust signals for a wide range of markets

Intermarket analysis studies interrelationships between various related markets. Standard correlations between markets are not useful if our goal is to either predict future prices or generate profitable signals because current correlation does not tell us anything about future prices. A methodology we originally developed in the mid 1990´s called intermarket divergence allows us to gauge the predictive power of an intermarket relationship and produce 100% objective signals. During the past 17 years we have used this methodology to develop trading systems which have produced robust and reliable trading signals even 17 years after the models were originally developed without any re-optimization. Other methodologies of processing intermarket relationships to develop trading signals might perform as well during in sample periods, but do not perform as well during walk forward period and during real trading. In this paper we will explain intermarket divergence and show how this methodology can be applied to a wide range of markets and how it performs better out of sample than other methodologies. Next we will analyze this methodology closer and try to understand why it works so well and how this basic methodology can be improved. The Intermarket divergence concept is also easy to enhance with various machine learning methods such as neural networks, SVM or rough sets. We will lay out a framework for this analysis.