Uniform Crossover in Genetic Algorithms
Proceedings of the 3rd International Conference on Genetic Algorithms
Technical market indicators optimization using evolutionary algorithms
Proceedings of the 10th annual conference companion on Genetic and evolutionary computation
Multiobjective optimization of technical market indicators
Proceedings of the 11th Annual Conference Companion on Genetic and Evolutionary Computation Conference: Late Breaking Papers
Using a GPU-CPU architecture to speed up a GA-based real-time system for trading the stock market
Soft Computing - A Fusion of Foundations, Methodologies and Applications - Special Issue on Evolutionary Computation on General Purpose Graphics Processing Units
On the utility of trading criteria based retraining in forex markets
EvoApplications'13 Proceedings of the 16th European conference on Applications of Evolutionary Computation
Combining technical analysis and grammatical evolution in a trading system
EvoApplications'13 Proceedings of the 16th European conference on Applications of Evolutionary Computation
Cartesian genetic programming for trading: a preliminary investigation
AusDM '12 Proceedings of the Tenth Australasian Data Mining Conference - Volume 134
| Hi-index | 0.00 |
Nowadays, there are two types of financial analysis oriented to design trading systems: fundamental and technical. Fundamental analysis consists in the study of all information (both financial and nonfinancial) available on the market, with the aim of carrying out efficient investments. By contrast, technical analysis works under the assumption that when we analyze the price action in a specific market, we are (indirectly) analyzing all the factors related to the market. In this paper we propose the use of an Evolutionary Algorithm to optimize the parameters of a trading system which combines Fundamental and Technical analysis (indicators). The algorithm takes advantage of a new operator called Filling Operator which avoids problems of premature convergence and reduce the number of evaluations needed. The experimental results are promising, since when the methodology is applied to values of 100 companies in a year, they show a possible return of 830% compared with a 180% of the Buy and Hold strategy.