2015
DOI: 10.1016/j.eswa.2015.05.013
|View full text |Cite
|
Sign up to set email alerts
|

Evaluating multiple classifiers for stock price direction prediction

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

12
223
1
4

Year Published

2015
2015
2024
2024

Publication Types

Select...
7
2

Relationship

0
9

Authors

Journals

citations
Cited by 459 publications
(273 citation statements)
references
References 67 publications
12
223
1
4
Order By: Relevance
“…Then, we apply the optimized neural network Nonlinear Autoregressive Exogenous (NARX) is applied to predict the stock price, whether buy, sell or hold the shares. Finally, the prediction is evaluated by the cost function as explained in equation (13). We have also performed a comparative study of the prediction between prominent stock market and emerging stock market.…”
Section: Architecture Of the Proposed Systemmentioning
confidence: 99%
See 1 more Smart Citation
“…Then, we apply the optimized neural network Nonlinear Autoregressive Exogenous (NARX) is applied to predict the stock price, whether buy, sell or hold the shares. Finally, the prediction is evaluated by the cost function as explained in equation (13). We have also performed a comparative study of the prediction between prominent stock market and emerging stock market.…”
Section: Architecture Of the Proposed Systemmentioning
confidence: 99%
“…Classification and various machine learning algorithms which use combination of classifiers are also gaining researchers' attention in dealing with the stock prediction. Among the various classification methods, some of the researchers use single classification for stock forecasting, whereas others use combination of multiple classifiers to improve the accuracy of prediction [13]. proposed of applying combination of technical analysis and nearest neighbour classification in predicting Brazilian stock market.…”
Section: Use Of Classification In Stock Prediction Systems and Their mentioning
confidence: 99%
“…Akcijų rinkos prognozavimas turi didelę reikšmę priimant investavimo sprendimus (Guresen et al 2011). Deja, akcijų kainos juda atsitiktinai, yra susijusios su istoriniais duomenimis, o pati akcijų rinka yra sudėtinga ir netiesiška sistema (Lo, MacKinlay 2011;Manahov, Hudson 2014), kurią sudaro daug skirtingų dalyvių, veikiančių pagal atskirus ekonominius, politinius ir psichologinius veiksnius (Ballings et al 2015), kurie gali padidinti rinkoje esamą neapibrėžtumą, o šis savo ruožtu gali turėti teigiamą arba neigiamą poveikį akcijų kainoms. Todėl labai svarbu siekti prognozavimo stabilumo, kad kuo tiksliau ir laiku būtų galima nustatyti tam tikrą nežinomų duomenų kiekį (Maknickienė, Maknickas 2012).…”
Section: Prielaidos Investavimo Sprendimų Priėmimo Modeliams Kurtiunclassified
“…It is observed from the study results that local modeling improves the performance. Michel Ballings et al [8] compare the ensemble methods such as Random Forest, AdaBoost and Kernel Factory against the single classifier models namely Neural Networks, Logistic Regression, Support Vector Machines and K-Nearest Neighbor. The data from 5767 European companies are taken for the study.…”
Section: Related Workmentioning
confidence: 99%