Akademik Veri Yönetim Sistemi
Journal of Emerging Computer Technologies, cilt.2, sa.1, ss.7-12, 2022 (Hakemli Dergi)
The prediction of any commodities such as cryptocurrency, stocks, silver, gold is a challenging task for the investors, researchers, and analysts. In this work, we propose a model that forecasts the value of 1 ounce of gold in dollars by using regression ensemble-based approaches. To our knowledge, this is the very first study in terms of combining regression models for the prediction of XAU/USD index although there are plenty of methods employed in the literature to forecast the price of gold. The contributions of this study are fivefold. First, the dataset is gathered between July 2019 and July 2020 from global financial websites in the world, and cleaned for modeling. Then, feature space is extended with technical and statistical indicators in addition to opening, closing, highest, lowest prices of gold index. Next, different regression and ensemble-based regression models are carried out. These are linear regression, polynomial regression, decision tree regression, random forest regression, support vector regression, voting regressor, stacking regressor. Experiment results demonstrate that the usage of stacking regression combination model exhibits considerable results with 2.2036 of MAPE for forecasting the price of XAU/USD index.