Time Series Forecasting Using Machine Learning: Development and Extensions.
Sajjad Taghiyeh · NCSU Libraries Repository (North Carolina State University Libraries) · 2020
This dissertation addresses two time series forecasting tasks: improving time series forecasting accuracy and time series forecasting model selection.In both problems, machine learning techniques are used to achieve the goal.The first problem is investigated using a hierarchical forecasting perspective.The goal is to improve the parent level forecasting accuracy using child level forecasts in a multi-level hierarchical environment.To achieve this goal, a multi-phase hierarchical forecasting