## Adaptive Genetic Programming for Option Pricing

### BibTeX

@MISC{Yin_adaptivegenetic,

author = {Zheng Yin and Anthony Brabazon},

title = {Adaptive Genetic Programming for Option Pricing},

year = {}

}

### OpenURL

### Abstract

Genetic Programming (GP) is an automated computational programming methodology, inspired by the workings of natural evolution techniques. It has been applied to solve complex problems in multiple domains including finance. This paper illustrates the application of an adaptive form of GP, where the probability of crossover and mutation is adapted dynamically during the GP run, to the important real-world problem of options pricing. The tests are carried out using market option price data and the results illustrate that the new method yields better results than are obtained from GP with fixed crossover and mutation rates. The developed method has potential for implementation across a range of dynamic problem environments. Categories and Subject Descriptors

### Citations

2866 |
Genetic Programming – On the Programming of Computers by Means of Natural Selection
- Koza
- 1992
(Show Context)
Citation Context ...al modeling [1]. A number of these algorithms draw metaphorical inspiration from processes of natural evolution. One of the most studied evolutionary methodologies is that of genetic programming (GP) =-=[12]-=-. GP is a population-based search algorithm. It starts from a high-level statement of what is required and automatically creates a computer programme to solve the problem. GP belongs to the field of E... |

696 | Genetic Programming II: Automatic Discovery of Reusable Programs - Koza - 1994 |

371 | Introduction to Evolutionary Computing
- Eiben, Smith
- 2003
(Show Context)
Citation Context ... 34.7 24.4 28.1 31.8 25.3 A.E. 42.9 55.5 84.7 95.1 99 133 137 147 157 189 114 another approach is to co-evolve the parameters during the run. Three broad methods of such adaptation exist (see Fig. 1) =-=[3]-=-. In this study we adopt the second approach. Dynamic Parameter Control Deterministic Feedback Adaptive Evolve the Parameters Figure 1: Taxonomy of adaptive parameter control Deterministic methods of ... |

225 |
Options, Futures and other Derivatives
- Hull
- 1997
(Show Context)
Citation Context ...1 Exchange Traded Options Exchange traded options have been actively traded on stocks, stock indices, foreign currencies and futures contracts by hedgers, speculators and arbitrageurs since the 1970s =-=[4]-=-. An option can be defined as the right but not the obligation to buy or sell a financial asset at a stated price at or during a specified time window. Option prices are affected by multiple factors. ... |

31 |
Biologically Inspired Algorithms for Financial Modelling
- Brabazon, O’Neill
- 2006
(Show Context)
Citation Context ... Terms Economics Keywords Genetic Programming, option pricing 1. INTRODUCTION Recent years have seen the application of multiple biologicallyinspired algorithms for the purposes of financial modeling =-=[1]-=-. A number of these algorithms draw metaphorical inspiration from processes of natural evolution. One of the most studied evolutionary methodologies is that of genetic programming (GP) [12]. GP is a p... |

12 | An Adaptive Evolutionary Approach to Option Pricing via Genetic Programming. NYU Working Paper No - Chidambaran, Lee, et al. - 1998 |

7 | Option Pricing with Genetic Programming
- Chen, Yeh, et al.
- 1998
(Show Context)
Citation Context ...ping closed form theoretical models for options pricing, the domain is particularly amenable to techniques such as GP. One of the early applications of GP to the option pricing problem is provided by =-=[19]-=-. Since then there have been many improvements such as seeding the initial population with elements drawn from the Black-Scholes option pricing formula, and the combination of other domain knowledge i... |

5 |
Genetic Programming with Monte Carlo Simulation for Option
- Chidambaran
- 2003
(Show Context)
Citation Context ...he probabilities of crossover and mutation were typically kept constant. For example, in [19] mutation is applied at a rate of 0.0033 with a level of 0.001 being applied by [15] and [20]. Chidambaran =-=[14]-=- investigated the utility of various mutation rates between 0.1 to 0.5 (each of which was constant in a single run). Generation Gap Between Two Neighbor Best Individuals 18 16 14 12 10 8 6 4 2 0 0 10 ... |

5 |
The Self-Evolving Logic Of Financial Claim Prices in Genetic algorithms and genetic programming in computational finance
- Noe, Wang
- 2002
(Show Context)
Citation Context ...of GP to options pricing, the probabilities of crossover and mutation were typically kept constant. For example, in [19] mutation is applied at a rate of 0.0033 with a level of 0.001 being applied by =-=[15]-=- and [20]. Chidambaran [14] investigated the utility of various mutation rates between 0.1 to 0.5 (each of which was constant in a single run). Generation Gap Between Two Neighbor Best Individuals 18 ... |

3 | Evolutionary computation in financial engineering: A road map of GAs and GP - Chen - 1998 |

2 |
Evolutionary Computation in Option Pricing: Determining Implied Volatilities Based on
- Keber
- 2002
(Show Context)
Citation Context ...options pricing, the probabilities of crossover and mutation were typically kept constant. For example, in [19] mutation is applied at a rate of 0.0033 with a level of 0.001 being applied by [15] and =-=[20]-=-. Chidambaran [14] investigated the utility of various mutation rates between 0.1 to 0.5 (each of which was constant in a single run). Generation Gap Between Two Neighbor Best Individuals 18 16 14 12 ... |

1 | Evolving Technical Trading Rules for Foreign-Exchange - Brabazon, O’Neill - 2004 |

1 | Option Valuation with Generalized Ant - Keber, Schuster - 2002 |

1 | Lexicographic Parsimony Pressure, Genetic and Evolutionary Computation Conference, 2002 - Luke, Panait - 2002 |

1 | Genetic Programming: A Tutorial with the Software Simple GP in Genetic algorithms and genetic programming in computational finance - Chen, Kuo, et al. - 2002 |

1 | A Nonparametric Approach to Pricing and Hedging Derivative Securities via Genetic Regression - Triqueros - 1997 |

1 |
Z.,Brabazon A.,O’Sulivan C. (2006). Genetic Programming and and Option Pricing
- Yin
(Show Context)
Citation Context ...vements such as seeding the initial population with elements drawn from the Black-Scholes option pricing formula, and the combination of other domain knowledge into the GP set of terminals / functions=-=[21]-=-. In this paper a new adaptive GP method is proposed where the probability of crossover and mutation is dynamically altered during the GP run. The method is benchmarked against a fixed parameter GP sy... |