Impact of Models and Eigenvalues on Gold Price Forecasting

Abstract

The burgeoning synergy between computer science and finance has fostered an increasing integration of these domains. Machine learning has become a prevalent tool in aiding financial analysis and forecasting. Compared to traditional forecasting techniques, machine learning-based models exhibit enhanced accuracy and broader applicability. This study introduces three models, namely linear regression, random forest, and support vector machine, to analyze and predict gold prices. The influence of Eigenvalues on model performance is also examined. In the end, the support vector machine model constructed by using two kinds of US dollar exchange rates, US Treasury bond interest rates, and the 10-day moving average of gold prices and passed cross-validation obtained the best model performance evaluation index, and its R2 index reached nearly 0.99. It can be concluded from this study that the performance of the model is poor when only one eigenvalue is used to build the model, while for the case of building a model with multiple eigenvalues, the contribution of the U.S. Treasury bond rate to the improvement of the performance of the prediction model is the smallest. Therefore, appropriately increasing the number of eigenvalues is conducive to improving the performance of the model, and selecting the types of eigenvalues reasonably is also conducive to improving the accuracy of the model.