No one can predict stock prices. However, there are many theories which imply that recurring seasonal effects could be used to determine the direction of share indices. Many traders have already heard the stock market adage: "Sell in May and go away, but remember to come back in September". What is with this adage really about, and are there other indications for the existence of recurring seasonal effects which could be used for respective trading strategies? This book deals with eleven different recurring seasonal effects which are frequently referred to in academic writings as well. Artificial neural networks are used to identify these phenomena at eight different underlyings. For underlyings, where a phenomenon could be identified, a trading strategy based on the forecast of artificial neural networks is presented. These strategies use the respective effect to determine the direction of share indices. In order to compare the trading results a comparative strategy is used as a benchmark. It is shown how artificial neural networks could be used to identify recurring seasonal effects and how to create a trading position depending on the signal of these effects.
Tim-Oliver Martens, Master of Science, Major Finance: Studies of Economy Science at the Gottfried Wilhelm Leibniz University of Hannover, Germany. Consultant at PricewaterhouseCoopers, Frankfurt am Main, Germany.