Yiu-ming Cheung

Independent component ordering in ICA time series analysis

Independent component analysis (ICA) has provided a new tool to analyze time series, which also gives rise to a question * how to order independent components? In the literature, some methods (Back and Trappenberg, Proceedings of International Joint Conference on Neural Networks, Vol. 2, 1999, pp. 989}992; HyvaK rinen, Neural Computing Surveys 2 (1999) 94; Back and Weigend, Int. J. Neural Systems 8(4) (1997) 473) have been suggested to decide the order based on each individual component without considering their interactions on the observed series. In this paper, we propose an alternative approach to order the components according to their joint contributions in data reconstruction, which naturally leads the component ordering to a typical combinatorial optimization problem, whereby the underlying optimum ordering can be found in an exhaustive way. To save computing costs, we also present a fast approximate search algorithm. The accompanying experiments have shown the outperformance of this new approach in comparison with an existing method. 2001 Elsevier Science B.V. All rights reserved.

Adaptive supervised learning decision networks for traders and portfolios

We propose an adaptive supervised learning decision network for portfolio management which learns the best past investment decision directly instead of making a good prediction first and then making an investment decision based on the prediction. Without any extra effort, this network can be realized directly by any existing adaptive supervised learning neural networks. We propose to use an extended normalized radial basis function (ENRBF) network with matched competitive learning (MCL). We demonstrate with experimental results that the proposed approach can bring in appreciable profit on trading in the foreign exchange market.

An empirical method to select dominant independent components in ICA for time series analysis

Back and Weigend (1997) showed that the dominant independent components obtained by independent component analysis (ICA) can reveal more underlying structure of the time series than principal component analysis. To find those dominant independent components, all the independent components are listed in an appropriate order and then a subset of components is selected according to the order. However, currently there does not exist a systematic way to choose such a subset. In this paper, we propose a number selection criterion to choose an appropriate dominant number, through which the dominant independent components can be automatically determined from a set of ordered components. Experiments on foreign exchange rates have shown the performance of this empirical method.

ADAPTIVE RIVAL PENALIZED COMPETITIVE LEARNING AND COMBINED LINEAR PREDICTOR MODEL FOR FINANCIAL FORECAST AND INVESTMENT

We propose a prediction model called Rival Penalized Competitive Learning (RPCL) and Combined Linear Predictor method (CLP), which involves a set of local linear predictors such that a prediction is made by the combination of some activated predictors through a gating network (Xu et al., 1994). Furthermore, we present its improved variant named Adaptive RPCL-CLP that includes an adaptive learning mechanism as well as a data pre-and-post processing scheme. We compare them with some existing models by demonstrating their performance on two real-world financial time series--a China stock price and an exchange-rate series of US Dollar (USD) versus Deutschmark (DEM). Experiments have shown that Adaptive RPCL-CLP not only outperforms the other approaches with the smallest prediction error and training costs, but also brings in considerable high profits in the trading simulation of foreign exchange market.

Rival Penalized Competitive Learning based approach for discrete-valued source separation.

This paper presents an approach based on Rival Penalized Competitive Learning (RPCL) rules for discrete-valued source separation. In this approach, we first build a connection between the source number and the cluster number of observations. Then, we use the RPCL rule to automatically find out the correct number of clusters such that the source number is determined. Moreover, we tune the de-mixing matrix based on the cluster centers instead of the observation themselves, whereby the noise interference is considerably reduced. The experiments have shown that this new approach not only quickly and automatically determines the number of sources, but also is insensitive to the noise in performing blind source separation.

A RPCL-CLP architecture for financial time series forecasting

In this paper, we propose a new architecture based on the rival penalized competitive learning algorithm (RPCL) of Xu, Krzyzak and Oja (1993) and combined linear prediction method (CLP). The performance of RPCL-CLP is insensitive to the initial number of cluster nodes selected. Experimental results show that it is robust in long-term prediction for financial time series forecasting.

Application of adaptive RPCL-CLP with trading system to foreign exchange investment

In this paper, an adaptive rival penalized competitive learning and combined linear prediction model is applied to the forecast of stock price and exchange rate. As shown by the experimental results, this approach not only is better than Elman net and MA(q) models in the criterion of root mean square error, but also can bring in more returns in the trade between US dollar and German Deutschmark with the association of a trading system. Moreover, whatever trading strategies with different risks are used in the trading system, adaptive RPCL-CLP can always keep the profits increasing as time goes through.

Adaptive Rival Penalized Competitive Learning and Combined Linear Predictor with application to financial investment

We have recently proposed an architecture called Rival Penalized Competitive Learning and Combined Linear Predictor (RPCL-CLP) to model financial time series with a certain degree of success (Cheung et al., 1995). Experiments have shown that RPCL-CLP outperforms ClusNet (Hsu et al., 1993), but it still has features which can be further improved. We propose a modified version called Adaptive RPCL-CLP which can automatically select the number of the initial cluster nodes for RPCL (Xu et al., 1993) and adaptively train the linear predictors parameters in each cluster node as well as the gating network. We apply it to the forecasting of foreign exchange rates and the Shanghai stock price. As shown by experiments, this adaptive version is much better than RPCL-CLP, and with a trading system it can bring in more returns in foreign exchange market trading.

Trading mechanisms and return volatility: empirical investigation on Shanghai Stock Exchange based on a neural network model

We empirically compare the behavior of open-to-open and close-to-close returns on the Shanghai Stock Exchange (SHSE) with different trading mechanisms (call market at the opening in the morning followed by continuous market). We use non-linear regression based on a neural network to study the volatility and efficiency of SHSE. The experimental results have shown that the volatility of the call market is significantly higher than that of the continuous market and the call market is more efficient than the continuous market.

A RPLC-based approach for identification of Markov model with unknown noise and number of states

(Krishnamurthy et al. 1993) studied one type of Hidden Markov Model (HMM) with identifying its state sequence and parameters based on the Expectation-Maximization (EM) algorithm, thus requiring extensive computing resources and a prior knowledge of state number. In this paper, we further study this model and present a new identification approach, which estimates the state sequence and HMM parameters through using the clustering information obtained via Rival Penalized Competitive Learning (RPCL) algorithm (Xu et al., 1992, 1993). Compared to Krishnamurthys method, our approach can not only fast identify the HMM, but also automatically find out the correct number of states. Experiments have successfully shown the performance of this approach.