Signal Decomposition and Stacking-Ensemble Learning Approaches Applied to Time Series Forecasting

Time series forecasting is an essential approach for businesses and researchers to make informed decisions by predicting future trends and patterns. Machine learning models are proposed for time series forecasting once they can capture the complex and nonlinear relationships in data. This thesis aims to evaluate the effectiveness of employing signal decomposition methods coupled with a stacking-ensemble learning approach for forecasting time series. For this, three applications are presented in this thesis. By analyzing the results, it was possible to identify that the proposed approach could reach lower forecasting errors outperforming the compared approaches. The proposed forecasting framework achieved errors lower than 3% in some scenarios. Compared to the other approaches, the proposed one presented a mean improvement performance ranging between 4.39% and 63.67%. Considering all findings, the hypothesis that the proposed approach improves the accuracy of the time series forecasting models is supported and should not be rejected.