Machine learning strategies for multi-step-ahead time series forecasting

Machine learning strategies for multi-step-ahead time series forecasting

How much electricity is going to be consumed for the next 24 hours? What will be the temperature for the next three days? What will be the number of sales of a certain product for the next few months? Answering these questions often requires forecasting several future observations from a given seque...

Full description

Bibliographic Details
Main Author: Ben Taieb, Souhaib
Other Authors: Bontempi, Gianluca
Format: Doctoral Thesis
Language:en
Published: Universite Libre de Bruxelles 2014
Subjects:
Informatique générale
Sciences exactes et naturelles
Machine learning
Time-series analysis > Data processing
Apprentissage automatique
Série chronologique > Informatique
forecasting competitions
load forecasting
nearest neighbors
neural networks
gradient boosting
direct forecasts
forecasting strategies
recursive forecasts
machine learning
time series forecasting
Online Access:http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/209234

Internet

http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/209234

Similar Items