Combining of random forest estimates using LSboost for stock market index prediction

A comprehensive evaluation of ensemble learning for stock-market prediction

“…To obtain answers to these questions, three well-used machine-learning algorithms, namely; decision trees (DTs), support vector machine (SVM) and a multilayer perceptron (MLP) neural networks, were employed. Using boosting, bagging, stacking, blending and simple maximum voting combination techniques, we, constructed twenty-five (25) different ensemble regressors and classifiers using DT, MLP and SVM for stock market prediction. We experimented our models on four available public stock-data from GSE, BSE, NYSE and JSE, and compared their accuracy and error metrics.…”

“…Pulido et al [38] ensembled NN with fuzzy incorporation (type-1 and type-2) for predicting the stock market [38], they achieved a high prediction accuracy by the proposed model compared with single NN classifier. An ensemble of trees in an RF using LSboost was carried out [25]; the study achieved reduced prediction error.…”

“…As observed in Table 1 (Appendix A), creating of ensemble classifiers and regressors in the domain of stock-market predictions has become an area of interest in recent studies. However, most of these studies [12,19,21,22,[24][25][26][27][28][29][30] were based on boosting (BOT) or bagging (BAG) combination method. Only a few [4,18,20,37] examined ensemble classifiers or regressors based on stacking or blending combinational technique.…”

“…Despite numerous works revealing the dominance of ensemble classifier over single classifier, most of these studies only ensemble a specific type of classifier or regressor for stock-market prediction, such as NN [18][19][20], DT [21,22] and SVM [12,23]. Also, most previous studies [12,19,21,22,[24][25][26][27][28][29][30], on ensemble methods for stock-market predictions adopted the decrease variance approach (boosting or bagging) and experimented with data from one country. Furthermore, a comparison between bagging (BAG) and boosting (BOT) combination techniques by [12,21] revealed that the BAG technique outperformed the BOT technique.…”

Stock Prediction by using NLP and Deep Learning Approach

“…Research work of Nonita Sharma et al [8] had given focus on to do prediction of the share prices by studying the historical data. For that they had taken decade data from the two well know indexes like NSE and BSE.…”