Genetic Programming in Statistical Arbitrage

Abstract. This paper employs genetic programming to discover statistical arbitrage strategies on the banking sector in the Euro Stoxx universe. Binary decision rules are evolved using two different representations. The first is the classical single tree approach, while the second is a dual tree structure where evaluation is contingent on the current market position. Hence, buy and sell rules are co-evolved. Both methods are capable of discovering significant statistical arbitrage strategies.

• Type: Conference
• Year: 2008
• Where: EVOW
• Authors: Philip Saks, Dietmar G. Maringer
• Keywords: Artificial Intelligence, Binary Decision Rules, EVOW 2008, Significant Statistical Arbitrage, Statistical Arbitrage Strategies