Machine Learning for Forecasting: A Comparative Analysis

Παπαδάκης, Κωνσταντίνος; Papadakis, Konstantinos

dc.contributor.author	Παπαδάκης, Κωνσταντίνος	el
dc.contributor.author	Papadakis, Konstantinos	en
dc.date.accessioned	2024-07-08T09:57:06Z
dc.date.available	2024-07-08T09:57:06Z
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/59817
dc.identifier.uri	http://dx.doi.org/10.26240/heal.ntua.27513
dc.rights	Αναφορά Δημιουργού-Μη Εμπορική Χρήση 3.0 Ελλάδα	*
dc.rights.uri	http://creativecommons.org/licenses/by-nc/3.0/gr/	*
dc.subject	Timeseries Forecasting	en
dc.subject	Deep Learning	en
dc.subject	Machine Learning	en
dc.subject	Data Science	en
dc.subject	Comparative Analysis	en
dc.subject	Πρόβλεψη Χρονοσειρών	el
dc.subject	Βαθιά Μάθηση	el
dc.subject	Μηχανική Μάθηση	el
dc.subject	Επιστήμη Δεδομένων	el
dc.title	Machine Learning for Forecasting: A Comparative Analysis	en
dc.contributor.department	AILS	el
heal.type	masterThesis
heal.secondaryTitle	Performance Assessment on Electricity Load and Traffic Datasets	en
heal.classification	Επιστήμη Δεδομένων	el
heal.classification	Data Science	en
heal.language	en
heal.access	free
heal.recordProvider	ntua	el
heal.publicationDate	2024-03-14
heal.abstract	This thesis investigates the performance of advanced machine learning models for time series forecasting. Prophet, N-BEATS, DeepAR, DeepVAR, and the Temporal Fusion Transformer are applied to the Electricity Load Diagrams and PEMS-SF datasets. Results are rigorously evaluated using appropriate forecasting metrics. The study highlights the strengths and weaknesses of each model in handling real-world data complexities, offering insights for choosing optimal forecasting methods based on data characteristics and problem domain.	en
heal.advisorName	Κόλλιας, Στέφανος	el
heal.advisorName	Kollias, Stephanos	en
heal.committeeMemberName	Στάμου, Γεώργιος	el
heal.committeeMemberName	Βουλόδημος, Αθανάσιος	el
heal.committeeMemberName	Stamou, Georgios	en
heal.committeeMemberName	Voulodimos, Athanasios	en
heal.academicPublisher	Εθνικό Μετσόβιο Πολυτεχνείο. Σχολή Ηλεκτρολόγων Μηχανικών και Μηχανικών Υπολογιστών	el
heal.academicPublisherID	ntua
heal.numberOfPages	95 σ.	el
heal.fullTextAvailability	false