Soft memory for stock market analysis using linear and developmental genetic programming

ABSTRACT

Recently, a form of memory usage was introduced for genetic programming (GP) called "soft memory." Rather than have a new value completely overwrite the old value in a register, soft memory combines the new and old register values. This work examines the performance of a soft memory linear GP and developmental GP implementation for stock trading. Soft memory is known to more slowly adapt solutions compared to traditional GP. Thus, it was expected to perform well on stock data which typically exhibit local turbulence in combination with an overall longer term trend. While soft memory and standard memory were both found to provide similar impressive accuracy in buys that produced profit and sells that prevented losses, the softer memory settings traded more actively. The trading of the softer memory systems produced less substantial cumulative gains than traditional memory settings for the stocks tested with climbing share price trends. However, the trading activity of the softer memory settings had moderate benefits in terms of cumulative profit compared to buy-and-hold strategy for share price trends involving a drop in prices followed later by gains.

REFERENCES

• 1: Anthony Brabazon , Michael O'Neill, Biologically Inspired Algorithms for Financial Modelling (Natural Computing Series), Springer-Verlag New York, Inc., Secaucus, NJ, 2006
• 2: Drezewski, R. and Sepielak, J. Evolutionary System for Generating Investment Strategies. Applications of Evolutionary Computing (EvoWorkshops 2009), Springer (2008), 83--92.
• 3: Grosan, Crina and Abraham, Ajith. Stock Market Modeling Using Genetic Programming Ensembles. Studies in Computational Intelligence 13, (2006), 131--146.
• 4: Nicholas Freitag McPhee , Riccardo Poli, Memory with memory: soft assignment in genetic programming, Proceedings of the 10th annual conference on Genetic and evolutionary computation, July 12-16, 2008, Atlanta, GA, USA [doi>10.1145/1389095.1389336]
• 5: Garnett Wilson , Wolfgang Banzhaf, Prediction of Interday Stock Prices Using Developmental and Linear Genetic Programming, Proceedings of the EvoWorkshops 2009 on Applications of Evolutionary Computing: EvoCOMNET, EvoENVIRONMENT, EvoFIN, EvoGAMES, EvoHOT, EvoIASP, EvoINTERACTION, EvoMUSART, EvoNUM, EvoSTOC, EvoTRANSLOG, April 15-17, 2009, Tübingen, Germany [doi>10.1007/978-3-642-01129-0_21]
• 6: Garnett Wilson , Malcolm Heywood, Introducing probabilistic adaptive mapping developmental genetic programming with redundant mappings, Genetic Programming and Evolvable Machines, v.8 n.2, p.187-220, June 2007 [doi>10.1007/s10710-007-9027-9]
• 7: Wei Yan , Martin V. Sewell , Christopher D. Clack, Learning to optimize profits beats predicting returns -: comparing techniques for financial portfolio optimisation, Proceedings of the 10th annual conference on Genetic and evolutionary computation, July 12-16, 2008, Atlanta, GA, USA [doi>10.1145/1389095.1389409]

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
      I.2.8 Problem Solving, Control Methods, and Search
          Subjects: Heuristic methods

General Terms:
Algorithms, Experimentation, Performance

Keywords:
developmental genetic programming, financial analysis, linear genetic programming