A hybrid model for high-frequency stock market forecasting

Araújo, Ricardo de A.; Oliveira, Adriano L. I.; Meira, Sílvio Romero de Lemos

doi:10.1016/j.eswa.2015.01.004

Cited by 39 publications

(13 citation statements)

References 65 publications

(74 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Several MNN have been presented in the literature to solve relevant problems, such as automatic target detection [12], landmine detection [13], handwritten character recognition [14], hyper spectral image analysis [15], time series forecasting [16], pattern recognition [17], computer vision [18], visionbased self-localization in mobile robotics [19], high-frequency financial data prediction [20], image understanding [21], amongst others.…”

Section: Ritter and Davidson Proposed The First Morphologicalmentioning

confidence: 99%

Training Algorithm for Dendrite Morphological Neural Network Using K-Medoids

Via¹,

Putra²,

Alit³

2018

Proceedings of the International Conference on Science and Technology (ICST 2018)

View full text Add to dashboard Cite

Pattern classification is one of the relevant problems in Artificial Intelligence. Neural networks have been studied as one of the most successful methods for pattern classification. Classical perceptron can only solve linear classification problems. Morphological Neural Networks (MNN) is an alternative way to solve classification problems in the form of linear and nonlinear. Dendrite Morphological Neural Networks (DMNN) is introduced as an improved method of classical MNN. The important problem that occurs in the DMNN training algorithm is to cluster objects with hyper boxes and classify each in the corresponding class. This paper presents the proposed training algorithm using K-medoids clustering algorithm to create the hyper boxes in the dimensional space. Kmedoids is better than other clustering methods in execution time and not sensitive to outliers. The implementation of the proposed algorithm will be involved in various simulations using artificial data sets and compared with other methods to evaluate the performance of this method in future work.

show abstract

Section: Ritter and Davidson Proposed The First Morphologicalmentioning

confidence: 99%

Training Algorithm for Dendrite Morphological Neural Network Using K-Medoids

Via¹,

Putra²,

Alit³

2018

Proceedings of the International Conference on Science and Technology (ICST 2018)

View full text Add to dashboard Cite

show abstract

“…Recently there has been a resurgence of interest in deep learning, whose basic structure is best described as a multilayer neural network [31]. Some literatures have established various models based on deep neural networks to improve the prediction ability of high-frequency financial time series [32,33]. The ability of deep neural networks to extract abstract features from data is also attractive, Chong et al [12] applied a deep feature learning-based stock market prediction model, which extract information from the stock return time series without relying on prior knowledge of the predictors and tested it on high-frequency data from the Korean stock market.…”

Section: Stock Market Prediction Methodmentioning

confidence: 99%

Stock Market Prediction on High-Frequency Data Using Generative Adversarial Nets

Zhou

Pan

et al. 2018

Mathematical Problems in Engineering

154

131

View full text Add to dashboard Cite

Stock price prediction is an important issue in the financial world, as it contributes to the development of effective strategies for stock exchange transactions. In this paper, we propose a generic framework employing Long Short-Term Memory (LSTM) and convolutional neural network (CNN) for adversarial training to forecast high-frequency stock market. This model takes the publicly available index provided by trading software as input to avoid complex financial theory research and difficult technical analysis, which provides the convenience for the ordinary trader of nonfinancial specialty. Our study simulates the trading mode of the actual trader and uses the method of rolling partition training set and testing set to analyze the effect of the model update cycle on the prediction performance. Extensive experiments show that our proposed approach can effectively improve stock price direction prediction accuracy and reduce forecast error.

show abstract

“…Such challenges typically arise in artificial neural network (ANN) training, where the input and output stream of data can be easily calculated though parameters are hidden inside the network (Pedersen and Chipperfield, 2010). Many applications of ANN have been presented over the last two decades, especially in finance (Ticknor, 2013;Kristjanpoller et al, 2014;Araújo et al, 2015;Fan et al, 2015;Patel et al, 2015aPatel et al, , 2015bRather et al, 2015). Most of these studies combine ANN with other optimization methods and algorithms such as PSO, which has demonstrated considerable success in ANN training (Das et al, 2013).…”

Section: Introductionmentioning

confidence: 99%

Evaluating the performances of over-the-counter companies in developing countries using a stochastic dominance criterion and a PSO-ANN hybrid optimization model

Nasseri¹,

Jamshidi²,

Yazdifar³

et al. 2020

JAAR

View full text Add to dashboard Cite

PurposeWith suitable optimization criteria, hybrid models have proven to be efficient for preparing portfolios in capital markets of developed countries. This study adapts and investigates these methods for a developing country, thus providing a novel approach to the application of banking and finance. Our specific objectives are to employ a stochastic dominance criterion to evaluate the performances of over-the-counter (OTC) companies in a developing country and to analyze them with a hybrid model involving particle swarm optimization and artificial neural networks.Design/methodology/approachIn order to achieve these aims, the authors conduct a case study of OTC companies in Iran. Weekly and daily returns of 36 companies listed in this market are calculated for one year during 2014–2015. The hybrid model is particularly interesting, and the results of the study identify first-, second- and third-order stochastic dominances among these companies. The study’s chosen model uses the best performing combination of activation functions in our analysis, corresponding to TPT, where T represents hyperbolic tangent transfers and P represents linear transfers.FindingsOur portfolios are based on the shares of companies ranked with respect to the stochastic dominance criterion. Considering the minimum and maximum numbers of shares to be 2 and 10 for each portfolio, an eight-share portfolio is determined to be optimal. Compared with the index of Iran OTC during the research period of this study, our selected portfolio achieves a significantly better performance. Moreover, the methods used in this analysis are shown to be as efficient as they were in the capital markets of developed countries.Research limitations/implicationsThe problem of optimizing investment portfolios has to allow for correlations among returns from the financial maintenance period under consideration if an asymmetric distribution of returns exists (Babaei et al., 2015). Therefore, it is desirable to select an appropriate criterion in order to prepare an optimal portfolio and prioritize investment options. Although a back propagation technique is very popular in artificial neural (ANN) training, it is time-consuming to train a network in this way, and other methods such as particle swarm optimization (PSO) should be considered instead. In the hybrid combination of PSO and ANN, it is not the structure of a neural network that changes. Rather, the weighting method and the training technique chosen for the network are the important aspects, and these relate to PSO, so the only role ANN plays in this process is to reduce the errors.Practical implicationsThe hybrid model combining ANN and PSO is seen to be considerably successful for generating optimal results and appropriate activation functions. These results are consistent with the theoretical findings of Das et al. (2013) and an application of the simple PSO in a study conducted by Pederson and Chipperfield (2010). Our research results also confirm the efficiency of stochastic dominance criteria as noted in the studies conducted by Roman et al. (2013), ANN as in a study carried out by Kristijanpoller et al. (2014) and PSO as in studies conducted by Liu et al. (2015) and Deng et al. (2012). These studies were carried out in the capital markets of developed countries, whereas the authors’ analysis relates to a developing country.Originality/valueThe authors deduce that the tools and methods whose efficiency was proven in the capital markets of developed countries also apply to, and demonstrate efficiency in, two novel applications of portfolio optimization within developing countries. The first of these is gaining familiarity with the theory and practice of these research tools and the methods that enrich financial knowledge of investors in developing countries. The second of these is the application of tools and methods identified by investors in the capital markets of developing countries, which enables optimal allocation of financial resources and growth of the markets. The authors expect that these findings will contribute to improving the economies of developing countries and thus help with economic development and facilitation of improving trends.

show abstract

A hybrid model for high-frequency stock market forecasting

Cited by 39 publications

References 65 publications

Training Algorithm for Dendrite Morphological Neural Network Using K-Medoids

Training Algorithm for Dendrite Morphological Neural Network Using K-Medoids

Stock Market Prediction on High-Frequency Data Using Generative Adversarial Nets

Evaluating the performances of over-the-counter companies in developing countries using a stochastic dominance criterion and a PSO-ANN hybrid optimization model

Contact Info

Product

Resources

About