| Sumario: | The establishment of an effective prediction model for the direction of stock market indices is quite challenging due to the complex and non-stationary nature of financial data. Predicting the upward or downward movements of the stock market index, especially in emerging market exchanges where the impacts of external factors and shocks are observed more deeply, is of significant importance to stakeholders such as investors, governments, financial institutions, and creditors, as well as researchers. The aim of this study is to predict the direction of the stock market index with tree-based ensemble Machine Learning (ML) methods. Technical Indicators calculated after applying Exponential Smoothing to daily Opening, Closing, Highest, Lowest and Volume data of three years were considered as input variables of the model. In addition, the input variable space was expanded by increasing the window lengths of the Technical Indicators. In the study, Random Forest, XGBoost and CatBoost methods, which based on Decision Trees, are used as ensemble ML methods. Bayesian Search was employed to determine the optimal parameters. According to the findings of the study, all selected methods demonstrated accuracy rates ranging from 89.7% to 90.4%, and considering other performance evaluation criterias, XGBoost was identified as the best prediction method.
|
|---|