A learning-to-forecast experiment on the foreign exchange market with a classifier system

Lin

2009

CMR

Security selection is the most time-consuming problem in investment process. Today, investing environment is more complex than before and investors can't see through the information frame, the reality behind which they are unable to scrutinize. Static model cannot provide appropriate solutions when current phenomena are completely different from that of the training period. Learning classifier system (LCS) is possessing with dynamically learning mechanism to evolve internal rules in response to changes in the external environment. This study employs real number version classifier system (XCSR) to investigate constructing dynamic stock portfolio. We examine the constituents of the TSEC Taiwan 50 Index and take those stocks daily transaction data to generate a number of technical indicators as input factors for XCSR model. The empirical results revealed that this study's XCSR model yields return on investment is significantly better than the Buy and Hold model. This research also indicates that classifier system can effectively monitor market fluctuations and the proposed model can help investors obtain relatively optimal returns.

Section: Investment Portfolio and Learning Classifier Systemmentioning

confidence: 99%

Application of XCSR Model for Dynamic Portfolio Selection

Lin

2009

CMR

“…Wilson's XCS model strives to achieve accuracy in forecasting returns, eliminates message list, adds prediction arrays and action sets in order to improve classifier system effectiveness, and uses Niche-genetic algorithms to implement evolution of rules. Beltrametti et al (1997) used an LCS model to study the foreign exchange market, the empirical results of this research showed that classifier systems can classify external information and generate suitable predictions, while evolving appropriate trading rules in response to environmental changes. Furthermore, other scholars have used classifier systems to analyze the trading of individual stocks using price indicators as inputs and individual stock sell signals as outputs.…”

Section: Classifier Systemsmentioning

confidence: 99%

Constructing a dynamic stock portfolio decision-making assistance model: using the Taiwan 50 Index constituents as an example

2007

There are several decisions in investment management process. Security selection is the most time-consuming stage. Tatical allocation is in order to take advantage of market opportunities based on short-term prediction (Amenc and Le Sourd in Portfolio theory and performance analysis. Wiley, 2003). Although it is difficult to keep track of the fluctuations of volatile financial markets, the capacity of artificial intelligence to perform spatial search and obtain feasible solutions has led to its recent widespread adoption in the resolution of financial problems. Classifier systems possess a dynamic learning mechanism, they can be used to constantly explore environmental conditions, and immediately provide appropriate decisions via self-aware learning. This study consequently employs a classifier system in conjunction with real number encoding to investigate how to obtain optimal stock portfolio based on investor adjustment cycle. We examine the constituents of the TSEC Taiwan 50 Index taking moving average (MA), stochastic indicators (KD), moving average convergence divergence (MACD), relative strength index (RSI) and Williams %R (WMS %R) as input factors, adopting investor-determined adjustment cycle to allocate capital, and then constructing stock portfolio. We have conducted empirical testing using weekly and monthly adjustment cycle; the results revealed that this study's decision-making assistance model yields average annual interest rate of 49.35%, which is significantly better than the −6.59% of a random purchase model. This research indicates that a classifier system can effectively monitor market fluctuations and help investors obtain relatively optimal returns. The assistance model proposed in this study thus can provide really helpful decision-making information to investors.

Proceedings of the 9th Joint International Conference on Information Sciences (JCIS-06)

“…The architecture of XCS is illustrated in Fig.1. The XCS operation model is described as follows: [ Beltrametti, Fiorentini, Marengo, and Tamborini (1997) apply Classifier System to the interaction of USD-DM and USD-JPY in foreign exchange market. This study shows the response of Classifier System towards dynamic changes of the exterior environment.…”

Section: Extended Classifier Systemmentioning

confidence: 99%

Applying XCS Model to Spread Trading of Taiwan Stock Index Futures

Li¹,

Fu²,

Chen³

2006

This study attempts to find the possibility of making relatively higher profit with lower risk when trading futures commodities. The system applies XCS classifiers to explore the rules of spread trading of these commodities. Our simulation holds a trading strategy that in every transaction, the proposed model buys and sells the same lots of goods of Taiwan index futures. All trades are settled by the end of each trading day.The outcome of this study shows that all the proposed three trading strategies that utilize XCS outperform spread trading decisions made by traditional buy low sell high strategy during the testing period. Regarding to the issue of profitability, intraday trading by XCS also has better performance than the control group. Hence this proposed shows its value in assisting investors to have extra reward without bearing higher risks.