A comprehensive cluster and classification mining procedure for daily stock market return forecasting

Zhong, Xiao; Enke, David

doi:10.1016/j.neucom.2017.06.010

Cited by 69 publications

(35 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…However, after the number of hidden layers becomes larger than 30 or 35, the accuracy of the classification for the testing data stops climbing and drops or converges to values that are close to the results using the ANN classifiers (which includes 10 hidden layers), except for one case where the transformed data with PCs = 60 and the number of hidden layers = 500 is considered. Note that the overfitting issue appears to be under control, in part since all the ANN and DNN classifiers are strictly trained with the same criteria, such that for each classifier the four correction percentages of the classification, corresponding to the training, validation, testing, and entire data sets cannot be significantly different from each other; that is, the absolute value of the percentage difference must be within a defined threshold, for example, 5% (Zhong & Enke, 2017a, 2017b. It is also observed that after the data are transformed via PCA, the average classification accuracy in the testing phase increases significantly.…”

Section: Comparison Of Classification Resultsmentioning

confidence: 99%

“…In previous studies (Zhong & Enke, 2017a, 2017b, the PCA-ANN classifiers are shown to give a higher prediction accuracy for the daily return direction of the SPY ETF for the next day than the FRPCA-ANN classifiers, KPCA-ANN classifiers, and logistic regression classifiers, with or without PCA/FRPCA/KPCA involved. Also, the trading strategies based on the PCA-ANN classifiers perform better than the other strategies based on the other classifiers.…”

Section: Conclusion and Suggestions For Future Workmentioning

confidence: 88%

See 1 more Smart Citation

Predicting the daily return direction of the stock market using hybrid machine learning algorithms

2019

Self Cite

View full text Add to dashboard Cite

Big data analytic techniques associated with machine learning algorithms are playing an increasingly important role in various application fields, including stock market investment. However, few studies have focused on forecasting daily stock market returns, especially when using powerful machine learning techniques, such as deep neural networks (DNNs), to perform the analyses. DNNs employ various deep learning algorithms based on the combination of network structure, activation function, and model parameters, with their performance depending on the format of the data representation. This paper presents a comprehensive big data analytics process to predict the daily return direction of the SPDR S&P 500 ETF (ticker symbol: SPY) based on 60 financial and economic features. DNNs and traditional artificial neural networks (ANNs) are then deployed over the entire preprocessed but untransformed dataset, along with two datasets transformed via principal component analysis (PCA), to predict the daily direction of future stock market index returns. While controlling for overfitting, a pattern for the classification accuracy of the DNNs is detected and demonstrated as the number of the hidden layers increases gradually from 12 to 1000. Moreover, a set of hypothesis testing procedures are implemented on the classification, and the simulation results show that the DNNs using two PCA-represented datasets give significantly higher classification accuracy than those using the entire untransformed dataset, as well as several other hybrid machine learning algorithms. In addition, the trading strategies guided by the DNN classification process based on PCA-represented data perform slightly better than the others tested, including in a comparison against two standard benchmarks.

show abstract

Section: Comparison Of Classification Resultsmentioning

confidence: 99%

Section: Conclusion and Suggestions For Future Workmentioning

confidence: 88%

Predicting the daily return direction of the stock market using hybrid machine learning algorithms

2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…Average of input vector for data sets may be stated as test magnitude of n whose effort quantity for test data as given in equation (12). As per the outcome of the proposed model Y-hat is fixed of predicted amounts and Y is a set of actual amounts used for prophecy.…”

Section: B Presentation Assessmentmentioning

confidence: 99%

“…To get better result of the financial predictions by help of few extra features in input of supervised models beside among historical data of the intention market. [12][13] used some stock market data in south korean stock and product costs in ANN based semisupervised model by not paying concentration to the historical data of the time series being expected and accomplished superior outcome contrast to their challenger by using only historical data of the objective. [13][14] suggested a model that supportive in projecting composite associations in between unexpected changes of financial data.…”

Section: Introductionmentioning

confidence: 99%

Advanced Deep Learning Framework for Stock Value Prediction

Das¹,

Mishra²

2019

IJITEE

View full text Add to dashboard Cite

The main attractive feature to stock market is speedy growth of stock economic value in short yoke of time. The investor analyses the demonstration, estimated value and growth of organizations before investing money in market. The analysis may not be enough by using conventional process or some available methods suggested by different researches. In present days large number of stocks are available in market it is very difficult to study each stock by help of very few suggested foretelling methods. To know the anticipated stock value we need some advanced prediction technology for stock market. This paper introduce an advanced skillful method to plan and analyze the different organizers stock execution in market and prognosticate best suitable stock by predicting close price of stock. The projected arrangement is based on multilayer deep learning neural Network optimized by Adam optimizer. Recent 6 years (2010-2016) data of different organizations are applied to the model to demonstrate the skillfulness of the projected proficient method. From result it has been ascertained that the projected framework is best suited to all different data set of various sectors. The prediction error is very minimal as visible from outcome graph of framework

show abstract

“…The relationship between the components was then transformed into vectors, with vectors with associations lower than a certain threshold being eliminated. Then, combination and text disambiguation were conducted (Zhong and Enke, 2017). In the third stage, the weights of the relationships were merged, and the merged components input into the ANN network input layer.…”

Section: Research Design and Data Collection 31 Modeling And Processingmentioning

confidence: 99%

Text mining based theme logic structure identification: application in library journals

Zhu

et al. 2018

LHT

View full text Add to dashboard Cite

Purpose Library intelligence institutions, which are a kind of traditional knowledge management organization, are at the frontline of the big data revolution, in which the use of unstructured data has become a modern knowledge management resource. The paper aims to discuss this issue. Design/methodology/approach This research combined theme logic structure (TLS), artificial neural network (ANN), and ensemble empirical mode decomposition (EEMD) to transform unstructured data into a signal-wave to examine the research characteristics. Findings Research characteristics have a vital effect on knowledge management activities and management behavior through concentration and relaxation, and ultimately form a quasi-periodic evolution. Knowledge management should actively control the evolution of the research characteristics because the natural development of six to nine years was found to be difficult to plot. Originality/value Periodic evaluation using TLS-ANN-EEMD gives insights into journal evolution and allows journal managers and contributors to follow the intrinsic mode functions and predict the journal research characteristics tendencies.

show abstract

A comprehensive cluster and classification mining procedure for daily stock market return forecasting

Cited by 69 publications

References 44 publications

Predicting the daily return direction of the stock market using hybrid machine learning algorithms

Predicting the daily return direction of the stock market using hybrid machine learning algorithms

Advanced Deep Learning Framework for Stock Value Prediction

Text mining based theme logic structure identification: application in library journals

Contact Info

Product

Resources

About