What is the best automatic forecasting method to deal with high frequency data and little human intervention?

Abstract

The aim of this thesis is to study which automatic forecasting method, betweenthe Theta and Prophet models, can return the most appropriate predictions aboutthe future, by computing two different performance metrics and with the use ofthree different ways of an out-of-sample cross-validation to successfully train themodels.Hence, it seems that Prophet has more difficulty to capture good predictionswhen working with certain nature of data when compared to the Theta model.Another relevant note is that the out-of-sample approach using the growing windowand one-fold type of cross-validation seems to perform better, when looking toall series used is this research. In addition, the Prophet model also has a highercomputational cost in terms of time to make its predictions. Further, it shouldalso be noted that the forecasts, in this analysis, regarding markets prices and themarket yield are computed to calculate their expected value, however it is very hardto estimate this. So, the justification for using this type of information is relatedto the fact that it is more common to find daily values in this context and themodels work better with daily observations. This exercise was attempted basedon easily available series and with merely illustrative purposes, in order to make acomparative evaluation of the two models.For these reasons, the Theta model is the best automatic forecasting method interms of results and computational costs when compared to the Prophet model.

Date of Award	26 Jan 2023
Original language	English
Awarding Institution	Universidade Católica Portuguesa
Supervisor	Pedro Afonso Fernandes (Supervisor)