Deep learning networks are applied to stock market analysis and prediction.A comprehensive analysis with different data representation methods is offered.Five-minute intraday data from the Korean KOSPI stock market is used.The network applied to residuals of autoregressive model improves prediction.Covariance estimation for market structure analysis is improved with the network. We offer a systematic analysis of the use of deep learning networks for stock market analysis and prediction. Its ability to extract features from a large set of raw data without relying on prior knowledge of predictors makes deep learning potentially attractive for stock market prediction at high frequencies. Deep learning algorithms vary considerably in the choice of network structure, activation function, and other model parameters, and their performance is known to depend heavily on the method of data representation. Our study attempts to provides a comprehensive and objective assessment of both the advantages and drawbacks of deep learning algorithms for stock market analysis and prediction. Using high-frequency intraday stock returns as input data, we examine the effects of three unsupervised feature extraction methodsprincipal component analysis, autoencoder, and the restricted Boltzmann machineon the networks overall ability to predict future market behavior. Empirical results suggest that deep neural networks can extract additional information from the residuals of the autoregressive model and improve prediction performance; the same cannot be said when the autoregressive model is applied to the residuals of the network. Covariance estimation is also noticeably improved when the predictive network is applied to covariance-based market structure analysis. Our study offers practical insights and potentially useful directions for further investigation into how deep learning networks can be effectively used for stock market analysis and prediction.

Deep learning networks for stock market analysis and prediction

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

In this paper, a generalized multiple-kernel fuzzy C-means (FCM) (MKFCM) methodology is introduced as a framework for image-segmentation problems. In the framework, aside from the fact that the composite kernels are used in the kernel FCM (KFCM), a linear combination of multiple kernels is proposed and the updating rules for the linear coefficients of the composite kernel are derived as well. The proposed MKFCM algorithm provides us a new flexible vehicle to fuse different pixel information in image-segmentation problems. That is, different pixel information represented by different kernels is combined in the kernel space to produce a new kernel. It is shown that two successful enhanced KFCM-based image-segmentation algorithms are special cases of MKFCM. Several new segmentation algorithms are also derived from the proposed MKFCM framework. Simulations on the segmentation of synthetic and medical images demonstrate the flexibility and advantages of MKFCM-based approaches.

A Multiple-Kernel Fuzzy C-Means Algorithm for Image Segmentation

The stock market is a key pivot in every growing and thriving economy, and every investment in the market is aimed at maximising profit and minimising associated risk. As a result, numerous studies have been conducted on the stock-market prediction using technical or fundamental analysis through various soft-computing techniques and algorithms. This study attempted to undertake a systematic and critical review of about one hundred and twenty-two (122) pertinent research works reported in academic journals over 11 years (2007–2018) in the area of stock market prediction using machine learning. The various techniques identified from these reports were clustered into three categories, namely technical, fundamental, and combined analyses. The grouping was done based on the following criteria: the nature of a dataset and the number of data sources used, the data timeframe, the machine learning algorithms used, machine learning task, used accuracy and error metrics and software packages used for modelling. The results revealed that 66% of documents reviewed were based on technical analysis; whiles 23% and 11% were based on fundamental analysis and combined analyses, respectively. Concerning the number of data source, 89.34% of documents reviewed, used single sources; whiles 8.2% and 2.46% used two and three sources respectively. Support vector machine and artificial neural network were found to be the most used machine learning algorithms for stock market prediction.

A systematic review of fundamental and technical analysis of stock market predictions

Stock price prediction using support vector regression on daily and up to the minute prices

Support vector regression has been applied to stock market forecasting problems. However, it is usually needed to tune manually the hyperparameters of the kernel functions. Multiple-kernel learning was developed to deal with this problem, by which the kernel matrix weights and Lagrange multipliers can be simultaneously derived through semidefinite programming. However, the amount of time and space required is very demanding. We develop a two-stage multiple-kernel learning algorithm by incorporating sequential minimal optimization and the gradient projection method. By this algorithm, advantages from different hyperparameter settings can be combined and overall system performance can be improved. Besides, the user need not specify the hyperparameter settings in advance, and trial-and-error for determining appropriate hyperparameter settings can then be avoided. Experimental results, obtained by running on datasets taken from Taiwan Capitalization Weighted Stock Index, show that our method performs better than other methods.

http://itlab.ee.nsysu.edu.tw/paper/A%20Multiple-Kernel%20Support%20Vector%20Regression%20Approach%20for%20Stock%20Market%20Price%20Forecasting.pdf

A multiple-kernel support vector regression approach for stock market price forecasting

Support vector clustering (SVC) has been successfully applied to solve multi-class classification problems. However, it is usually hard to determine the hyper-parameters of RBF kernel functions. A multiple kernel learning (MKL) algorithm is developed to solve this problem, by which the kernel matrix weights and Lagrange multipliers can be simultaneously obtained with semidefinite programming. However, the amount of time and space required is very demanding. We develop a two stage multiple kernel learning algorithm by incorporating sequential minimal optimization (SMO) with the gradient projection method. Experimental results on data sets from UCI and Statlog show that the proposed approach outperforms single-kernel support vector clustering.

/pdf/multi-kernel-support-vector-clustering-for-multi-class-531g7igo1j.pdf

Multi-Kernel Support Vector Clustering for Multi-Class Classification

. Recently, vehicle similarity learning, also called re-identiﬁcation (ReID), has attracted signiﬁcant attention in computer vision. Several algorithms have been developed and obtained considerable success. However, most existing methods have unpleasant performance in the hazy scenario due to poor visibility. Though some strategies are possible to resolve this problem, they still have room to be improved due to the limited performance in real-world scenarios and the lack of real-world clear ground truth. Thus, to resolve this problem, inspired by CycleGAN, we construct a training paradigm called RVSL which integrates ReID and domain transformation techniques. The network is trained on semi-supervised fashion and does not require to employ the ID labels and the corresponding clear ground truths to learn hazy vehicle ReID mission in the real-world haze scenes. To further constrain the unsupervised learning process effectively, several losses are developed. Experimental results on synthetic and real-world datasets indicate that the proposed method can achieve state-of-the-art performance on hazy vehicle ReID problems. It is worth mentioning that although the proposed method is trained without real-world label information, it can achieve competitive performance compared to existing supervised methods trained on complete label information.

RVSL: Robust Vehicle Similarity Learning in Real Hazy Scenes Based on Semi-supervised Learning

The method for forecasting stock price based on multiple- kernel support vector regression (SVR) of the present invention includes the steps of: (a) setting characteristics by using stock prices x days before or/and various technical indexes; (b) constructing kernel matrix according to the characteristics, kernel functions and hyperparameters; (c) calculating an optimum kernel matrix weight and an optimum Lagrange multiplier by using iteration method to update the Lagrange multipliers by fixing every kernel matrix weight of the kernel matrixes in linear combination and update the kernel matrix weights by fixing the updated Lagrange multipliers, wherein the iteration method is stopped when the stopping criterion is meet; and (d) forecasting the future trend of stock price according to the optimum kernel matrix weight and the optimum Lagrange multiplier. Whereby, problems of conventional SVRs, every type of regression, a great amount of data and data classification are improved, and the method of the present invention has the excellent ability to forecast the stock price.

Chi-Yuan Yeh

Papers

A multiple-kernel support vector regression approach for stock market price forecasting

Multi-Kernel Support Vector Clustering for Multi-Class Classification

RVSL: Robust Vehicle Similarity Learning in Real Hazy Scenes Based on Semi-supervised Learning

Method for forecasting stock price based on multiple-kernel support vector regression