Due to the inherent non-linearity and non-stationary characteristics of financial stock market price time series, conventional modeling techniques such as the Box-Jenkins autoregressive integrated moving average (ARIMA) are not adequate for stock market price forecasting. In this paper, a forecasting model based on chaotic mapping, firefly algorithm, and support vector regression (SVR) is proposed to predict stock market price. The forecasting model has three stages. In the first stage, a delay coordinate embedding method is used to reconstruct unseen phase space dynamics. In the second stage, a chaotic firefly algorithm is employed to optimize SVR hyperparameters. Finally in the third stage, the optimized SVR is used to forecast stock market price. The significance of the proposed algorithm is 3-fold. First, it integrates both chaos theory and the firefly algorithm to optimize SVR hyperparameters, whereas previous studies employ a genetic algorithm (GA) to optimize these parameters. Second, it uses a delay coordinate embedding method to reconstruct phase space dynamics. Third, it has high prediction accuracy due to its implementation of structural risk minimization (SRM). To show the applicability and superiority of the proposed algorithm, we selected the three most challenging stock market time series data from NASDAQ historical quotes, namely Intel, National Bank shares and Microsoft daily closed (last) stock price, and applied the proposed algorithm to these data. Compared with genetic algorithm-based SVR (SVR-GA), chaotic genetic algorithm-based SVR (SVR-CGA), firefly-based SVR (SVR-FA), artificial neural networks (ANNs) and adaptive neuro-fuzzy inference systems (ANFIS), the proposed model performs best based on two error measures, namely mean squared error (MSE) and mean absolute percent error (MAPE).

Support vector regression with chaos-based firefly algorithm for stock market price forecasting

Multi-kernel extreme learning machine based method is proposed for EEG classification.Supplementary information from different kernels are integrated for better accuracy.Extensive experimental comparison confirms superiority of the proposed method. One of the most important issues for the development of a motor-imagery based brain-computer interface (BCI) is how to design a powerful classifier with strong generalization capability. Extreme learning machine (ELM) has recently proven to be comparable or more efficient than support vector machine for many pattern recognition problems. In this study, we propose a multi-kernel ELM (MKELM)-based method for motor imagery electroencephalogram (EEG) classification. The kernel extension of ELM provides an elegant way to circumvent calculation of the hidden layer outputs and inherently encode it in a kernel matrix. We investigate effects of two different kernel functions (i.e., Gaussian kernel and polynomial kernel) on the performance of kernel ELM. The MKELM method is subsequently developed by integrating these two types of kernels with a multi-kernel learning strategy, which can effectively explore the supplementary information from multiple nonlinear feature spaces for more robust classification of EEG. An extensive experimental comparison with two public EEG datasets indicates that the MKELM method gives higher classification accuracy than those of the other competing algorithms. The experimental results confirm that superiority of the proposed MKELM-based method for accurate classification of EEG associated with motor imagery in BCI applications. Our method also provides a promising and generalized solution to investigate the complex and nonlinear information for various applications in the fields of expert and intelligent systems.

Multi-kernel extreme learning machine for EEG classification in brain-computer interfaces

The first systematic literature review on evolutionary rule discovery in stock algorithmic trading.A clear demonstrate of studies in this field based on a classification framework.A precise analysis of gaps and limitations in existing studies based on detail of evaluation scheme.The most important factors influencing profitability of models are presented in detail.Targeted suggestions for future improvements based on the review are proposed. Despite the wide application of evolutionary computation (EC) techniques to rule discovery in stock algorithmic trading (AT), a comprehensive literature review on this topic is unavailable. Therefore, this paper aims to provide the first systematic literature review on the state-of-the-art application of EC techniques for rule discovery in stock AT. Out of 650 articles published before 2013 (inclusive), 51 relevant articles from 24 journals were confirmed. These papers were reviewed and grouped into three analytical method categories (fundamental analysis, technical analysis, and blending analysis) and three EC technique categories (evolutionary algorithm, swarm intelligence, and hybrid EC techniques). A significant bias toward the applications of genetic algorithm-based (GA) and genetic programming-based (GP) techniques in technical trading rule discovery is observed. Other EC techniques and fundamental analysis lack sufficient study. Furthermore, we summarize the information on the evaluation scheme of selected papers and particularly analyze the researches which compare their models with buy and hold strategy (B&H). We observe an interesting phenomenon where most of the existing techniques perform effectively in the downtrend and poorly in the uptrend, and considering the distribution of research in the classification framework, we suggest that this phenomenon can be attributed to the inclination of factor selections and problem in transaction cost selections. We also observe the significant influence of the transaction cost change on the margins of excess return. Other influenced factors are also presented in detail. The absence of ways for market trend prediction and the selection of transaction cost are two major limitations of the studies reviewed. In addition, the combination of trading rule discovery techniques and portfolio selection is a major research gap. Our review reveals the research focus and gaps in applying EC techniques for rule discovery in stock AT and suggests a roadmap for future research.

Application of evolutionary computation for rule discovery in stock algorithmic trading

Clustering-based ensembles for one-class classification

Evolutionary Fuzzy Systems are a successful hybridization between fuzzy systems and Evolutionary Algo- rithms. They integrate both the management of imprecision/uncertainty and inherent interpretability of Fuzzy Rule Based Systems, with the learning and adaptation capabilities of evolutionary optimization. Over the years, many different approaches in Evolutionary Fuzzy Systems have been developed for improving the behavior of fuzzy systems, either acting on the Fuzzy Rule Base Systems' elements, or by defining new approaches for the evolutionary components. All these efforts have enabled Evolutionary Fuzzy Systems to be successfully applied in several areas of Data Mining and engineering. In accordance with the former, a wide number of applications have been also taken advantage of these types of systems. However, with the new advances in computation, novel problems and challenges are raised every day. All these issues motivate researchers to make an effort in releasing new ways of addressing them with Evolutionary Fuzzy Systems. In this paper, we will review the progression of Evolutionary Fuzzy Systems by analyzing their taxon- omy and components. We will also stress those problems and applications already tackled by this type of approach. We will present a discussion on the most recent and difficult Data Mining tasks to be addressed, and which are the latest trends in the development of Evolutionary Fuzzy Systems.

/pdf/revisiting-evolutionary-fuzzy-systems-taxonomy-applications-2ss13ccr8b.pdf

Revisiting Evolutionary Fuzzy Systems: Taxonomy, applications, new trends and challenges

We present an application of type-2 neuro-fuzzy modeling to stock price prediction based on a given set of training data. Type-2 fuzzy rules can be generated automatically by a self-constructing clustering method and the obtained type-2 fuzzy rules cab be refined by a hybrid learning algorithm. The given training data set is partitioned into clusters through input-similarity and output-similarity tests, and a type-2 TSK rule is derived from each cluster to form a fuzzy rule base. Then the antecedent and consequent parameters associated with the rules are refined by particle swarm optimization and least squares estimation. Experimental results, obtained by running on several datasets taken from TAIEX and NASDAQ, demonstrate the effectiveness of the type-2 neuro-fuzzy modeling approach in stock price prediction.

Application of type-2 neuro-fuzzy modeling in stock price prediction

Finding an efficient method to detect counterfeit banknotes is an imperative task in business transactions. In this paper, we propose a system based on multiple-kernel support vector machines for counterfeit banknote recognition. A support vector machine (SVM) to minimize false rates is developed. Each banknote is divided into partitions and the luminance histograms of the partitions are taken as the input of the system. Each partition is associated with its own kernels. Linearly weighted combination is adopted to combine multiple kernels into a combined matrix. Optimal weights with kernel matrices in the combination are obtained through semi-definite programming (SDP) learning. Two strategies are adopted to reduce the amount of time and space required by the SDP method. One strategy assumes the non-negativity of the kernel weights, and the other one is to set the sum of the weights to be unity. Experiments with Taiwanese banknotes show that the proposed approach outperforms single-kernel SVMs, standard SVMs with SDP, and multiple-SVM classifiers.

/pdf/employing-multiple-kernel-support-vector-machines-for-29dcy8hir7.pdf

Employing multiple-kernel support vector machines for counterfeit banknote recognition

AdaBoost.M1 has been successfully applied to improve the accuracy of a learning algorithm for multi-class classification problems. However, it may be hard to satisfy the required conditions in some practical cases. An improved algorithm called AdaBoost.MK is developed to solve this problem. Early proposed support vector machines (SVM)-based, multi-class classification algorithms work by splitting the original problem into a set of two-class subproblems. The amount of time and space required by these algorithms is very demanding. We develop a multi-class classification algorithm by incorporating one-class SVMs with a well-designed discriminant function. Finally, a hybrid method integrating AdaBoost.MK and one-class SVMs is proposed to solve multi-class classification problems. Experimental results on data sets from UCI and Statlog show that the proposed approach outperforms other multi-class algorithms, such as support vector data descriptions (SVDDs) and AdaBoost.M1 with one-class SVMs, and the improvement is found to be statistically significant.

Boosting One-Class Support Vector Machines for Multi-Class Classification

Support vector machines (SVMs) have been broadly applied to classification problems. However, a successful application of SVMs depends heavily on the determination of the right type and suitable hyperparameter settings of kernel functions. Recently, multiple-kernel learning (MKL) algorithms have been developed to deal with these issues by combining different kernels together. The weight with each kernel in the combination is obtained through learning. Lanckriet et al. proposed a way of deriving the weights by transforming the learning into a semidefinite programming (SDP) problem with a transduction setting. However, the amount of time and space required by this method is demanding. In this paper, we reformulate the SDP problem with an induction setting and incorporate two strategies to reduce the search complexity of the learning process, based on the comments discussed in the Lanckriet et al. paper. The primal and dual forms of SDP are derived. A discussion on computation complexity is given. Experimental results obtained from synthetic and benchmark datasets show that the proposed method runs efficiently in multiple-kernel learning.

An efficient multiple-kernel learning for pattern classification

We propose a clustering algorithm which incorporates a similarity-based fuzzy clustering and principal component analysis. The proposed algorithm is capable of discovering clusters with hyper-spherical, hyper-ellipsoidal, or oblique hyper-ellipsoidal shapes. Besides, the number of the clusters need not be specified in advance by the user. For a given dataset, the orientation, locations, and the number of clusters obtained can truthfully reflect the characteristics of the dataset. Experimental results, obtained by running on datasets generated synthetically, show that our method performs better than other methods.

/pdf/fuzzy-clustering-with-principal-component-analysis-4ztzyizrzk.pdf

Chi-Yuan Yeh

Papers

Application of type-2 neuro-fuzzy modeling in stock price prediction

Employing multiple-kernel support vector machines for counterfeit banknote recognition

Boosting One-Class Support Vector Machines for Multi-Class Classification

An efficient multiple-kernel learning for pattern classification

Fuzzy clustering with principal component analysis