Foreign Exchange Trading Using a Learning Classifier System

Stone, Christopher; Bull, Larry

doi:10.1007/978-3-540-78979-6_8

Cited by 3 publications

(2 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…, Gershoff [12], Schulenburg [15][16][17], Stone [20] etc have applied learning classifiers systems to different financial contexts such as the foreign exchanges market, the derivatives market and the equity market. While their results were promising, it is hypothesized that better results can be achieved by improving processes which surround the main XCS learning component.…”

Section: Introductionmentioning

confidence: 99%

Portfolio allocation using XCS experts in technical analysis, market conditions and options market

Wong

Schulenburg²

2007

Proceedings of the 9th Annual Conference Companion on Genetic and Evolutionary Computation

View full text Add to dashboard Cite

Schulenburg [15] first proposed the idea to model different trader types by supplying different input information sets to a group of homogenous LCS agent. Gershoff [12] investigated this idea further with XCS agent. This paper takes an extra step to build a trading system that not only adopts the multi-XCS agent idea, but also utilizes knowledge from discretization theory, modern portfolio theory, options theory and methods of combining multiple models. In comparison to previous work, a wider range of input data were used including technical analysis, general market conditions and options market conditions. Secondly, quantization of continuous financial series was achieved using entropy-based discretization and histogram equalization. Thirdly, subtle investment strategies can now be generated as a result of taking stock price magnitude into account. Finally, multiple agents' predictions were combined using a variant of stacking. Empirical results show the best-performing XCS agents always outclass benchmark agents in every stock examined. Variance is reduced after combining predictions from multiple models. The technical analysis XCS agent was able to replicate a well known technical trading rule widely used in the 60s.

show abstract

Section: Introductionmentioning

confidence: 99%

Portfolio allocation using XCS experts in technical analysis, market conditions and options market

Wong

Schulenburg²

2007

Proceedings of the 9th Annual Conference Companion on Genetic and Evolutionary Computation

View full text Add to dashboard Cite

show abstract

“…The important work of LCSs apply to multi-step [67], modifications for non-Markov and Markov environments [69,68], incorporation of continuous-valued actions [47], function approximation problem [37,64,121,123,15], boolean applications [66], and many others. LCSs have also been applied to various applications in the areas of data analysis and data mining [122,3,106], pattern recognition [113,126,16,91], robotics [80,55], classification [9,99,113] and computational economics [110]. Here, we review recent research that applied LCSs to the area of pattern recognition and classification.…”

Section: Lcss Applied To Pattern Classificationmentioning

confidence: 99%

Three-cornered coevolution learning classifier systems for classification

Marzukhi¹

View full text Add to dashboard Cite

<p>This thesis introduces a Three-Cornered Coevolution System that is capable of addressing classification tasks through coevolution (coadaptive evolution) where three different agents (i.e. a generation agent and two classification agents) learn and adapt to the changes of the problems without human involvement. In existing pattern classification systems, humans usually play a major role in creating and controlling the problem domain. In particular, humans set up and tune the problem’s difficulty. A motivation of the work for this thesis is to design and develop an automatic pattern generation and classification system that can generate various sets of exemplars to be learned from and perform the classification tasks autonomously. The system should be able to automatically adjust the problem’s difficulty based on the learners’ ability to learn (e.g. determining features in the problem that affect the learners’ performance in order to generate various problems for classification at different levels of difficulty). Further, the system should be capable of addressing the classification tasks through coevolution (coadaptive evolution), where the participating agents learn and adapt to the changes of the problems without human participation. Ultimately, Learning Classifier System (LCS) is chosen to be implemented in the participating agents. LCS has several potential characteristics, such as interpretability, generalisation capability and variations in representation, that are suitable for the system. The work can be broken down into three main phases. Phase 1 is to develop an automated evolvable problem generator to autonomously generate various problems for classification, Phase 2 is to develop the Two-Cornered Coevolution System for classification, and Phase 3 is to develop the Three-Cornered Coevolution System for classification. Phase 1 is necessary in order to create a set of problem domains for classification (i.e. image-based data or artificial data) that can be generated automatically, where the difficulty levels of the problem can be adjusted and tuned. Phase 2 is needed to investigate the generation agent’s ability to autonomously tune and adjust the problem’s difficulty based on the classification agent’s performance. Phase 2 is a standard coevolution system, where two different agents evolve to adapt to the changes of the problem. The classification agent evolves to learn various classification problems, while the generation agent evolves to tune and adjust the problem’s difficulty based on the learner’s ability to learn. Phase 3 is the final research goal. This phase develops a new coevolution system where three different agents evolve to adapt to the changes of the problem. Both of the classification agents evolve to learn various classification problems, while the generation agent evolves to tune and adjust the problem’s difficulty based on the classification agents’ ability to learn. The classification agents use different styles of learning techniques (i.e. supervised or reinforcement learning techniques) to learn the problems. Based on the classification agents’ ability (i.e. the difference in performance between the classification agents) the generation agent adjusts and creates various problems for classification at different levels of difficulty (i.e. various ‘hard’ problems). The Three-Cornered Coevolution System offers a great potential for autonomous learning and provides useful insight into coevolution learning over the standard studies of pattern recognition. The system is capable of autonomously generating various problems, learning and providing insight into each learning system’s ability by determining the problem domains where they perform relatively well. This is in contrast to humans having to determine the problem domains.</p>

show abstract

Identifying Trade Entry and Exit Timing Using Mathematical Technical Indicators in XCS

Preen

2010

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Foreign Exchange Trading Using a Learning Classifier System

Cited by 3 publications

References 25 publications

Portfolio allocation using XCS experts in technical analysis, market conditions and options market

Portfolio allocation using XCS experts in technical analysis, market conditions and options market

Three-cornered coevolution learning classifier systems for classification

Identifying Trade Entry and Exit Timing Using Mathematical Technical Indicators in XCS

Contact Info

Product

Resources

About