TY - JOUR
T1 - Speed up of the majority voting ensemble method for the prediction of stock price directions
AU - Moon, Kyoung Sook
AU - Jun, Sookyung
AU - Kim, Hongjoong
N1 - Funding Information:
The research of Kim was supported by Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education (NRF-2014R1A1A2058271). This work of Moon was supported by the Gachon University research fund of 2017.
PY - 2018
Y1 - 2018
N2 - The prediction of stock price directions is important in finance. The Majority Voting Ensemble method is superior in prediction accuracy to single classifier models including Logistic Regression, Decision Tree, K-Nearest Neighbors and Support Vector Machine, but the computational cost is very expensive since it considers all the hyperparameters of single classifier models. The current study proposes a revision of the majority voting method to improve the computational efficiency. The proposed method lets each single classifier model find its own hyperparameter values and this modification speeds up the computation by 500 times compared to the standard majority voting method while maintaining the accuracy. The numerical experiments show the ranking of the classifier models in the order of the proposed majority voting, the standard majority voting, and then other single classifier models including the support vector machine. This improvement will allow the majority voting ensemble method to be applied in the financial market in practice. The algorithms are tested on 7 national indices from 3 continents for the past 3 years, and the performance is measured in two criteria, the area under the receiver operating characteristic curve and the percent correctly classified.
AB - The prediction of stock price directions is important in finance. The Majority Voting Ensemble method is superior in prediction accuracy to single classifier models including Logistic Regression, Decision Tree, K-Nearest Neighbors and Support Vector Machine, but the computational cost is very expensive since it considers all the hyperparameters of single classifier models. The current study proposes a revision of the majority voting method to improve the computational efficiency. The proposed method lets each single classifier model find its own hyperparameter values and this modification speeds up the computation by 500 times compared to the standard majority voting method while maintaining the accuracy. The numerical experiments show the ranking of the classifier models in the order of the proposed majority voting, the standard majority voting, and then other single classifier models including the support vector machine. This improvement will allow the majority voting ensemble method to be applied in the financial market in practice. The algorithms are tested on 7 national indices from 3 continents for the past 3 years, and the performance is measured in two criteria, the area under the receiver operating characteristic curve and the percent correctly classified.
KW - Ensemble method
KW - Forecasting
KW - Machine learning
KW - Majority voting
KW - Stock price prediction
UR - http://www.scopus.com/inward/record.url?scp=85044733185&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85044733185&partnerID=8YFLogxK
U2 - 10.24818/18423264/52.1.18.13
DO - 10.24818/18423264/52.1.18.13
M3 - Article
AN - SCOPUS:85044733185
VL - 52
SP - 215
EP - 228
JO - Economic Computation and Economic Cybernetics Studies and Research
JF - Economic Computation and Economic Cybernetics Studies and Research
SN - 0585-7511
IS - 1
ER -