Back to search

Bc. Samuel Ambros

Master's thesis

Leveraging Machine Learning for Time Series Predictive Analysis

Leveraging Machine Learning for Time Series Predictive Analysis
Abstract:
Táto diplomová práca hodnotí efektívnosť jedenástich rôznych modelov prognózovania na viacerých súboroch údajov s rôznymi charakteristikami. Analyzované modely zahŕňajú lineárnu regresiu, ARIMA, SARIMAX, Prophet, ETS, DLT, KTR, LSTM, grafové neurónové siete, Transformer a automatizované modely strojového učenia pomocou AutoTS. Zistenia naznačujú, že žiadny model nie je jednotne lepší vo všetkých skúmaných …more
Abstract:
This thesis evaluates the effectiveness of eleven different forecasting models on multiple datasets with diverse characteristics. The models analyzed include linear regression, ARIMA, SARIMAX, Prophet, ETS, DLT, KTR, LSTM, Graph Neural Networks, Transformer models, and automated machine learning models using AutoTS. The findings suggest that no single model uniformly outperforms others across all datasets …more
 

Keywords

Time series forecasting Machine learning Python ARIMA SARIMAX Prophet ETS DLT KTR LSTM GNN Transformer AutoTS
 
Language used: English
Date on which the thesis was submitted / produced: 21. 5. 2024
Identifier: https://is.muni.cz/th/d7tnp/

Thesis defence

  • Date of defence: 20. 6. 2024
  • Supervisor: doc. Ing. RNDr. Barbora Bühnová, Ph.D.
  • Reader: doc. Ing. Radim Burget, Ph.D.

Citation record

Cite this text

Full text of thesis

Contents of on-line thesis archive
Published in Theses:
  • světu
Other ways of accessing the text
Institution archiving the thesis and making it accessible: Masarykova univerzita, Fakulta informatiky
Složka Reference to the local database directory of the institution