Meta-learning for time series forecasting and forecast combination

Authors:
Christiane Lemke;Bogdan Gabrys
Affiliations:
Smart Technology Research Centre, School of Design, Engineering and Computing, Bournemouth University, Poole House, Talbot Campus, Poole BH12 5BB, UK;Smart Technology Research Centre, School of Design, Engineering and Computing, Bournemouth University, Poole House, Talbot Campus, Poole BH12 5BB, UK
Venue:
Neurocomputing
Year:
2010

Citing 12
Cited 6

Rule-based forecasting: development and validation of an expert systems approach to combining time series extrapolations

Management Science
Bagging predictors

Machine Learning
Combining and selecting forecasting models using rule based induction

Computers and Operations Research
Ensemble learning via negative correlation

Neural Networks
A perspective view and survey of meta-learning

Artificial Intelligence Review
Ranking Learning Algorithms: Using IBL and Meta-Learning on Accuracy and Time Results

Machine Learning
Measures of Diversity in Classifier Ensembles and Their Relationship with the Ensemble Accuracy

Machine Learning
Selection of Time Series Forecasting Models based on Performance Information

HIS '04 Proceedings of the Fourth International Conference on Hybrid Intelligent Systems
Managing Diversity in Regression Ensembles

The Journal of Machine Learning Research
The lack of a priori distinctions between learning algorithms

Neural Computation
Rule induction for forecasting method selection: Meta-learning the characteristics of univariate time series

Neurocomputing
Using machine learning techniques to combine forecasting methods

AI'04 Proceedings of the 17th Australian joint conference on Advances in Artificial Intelligence

Editorial: European Symposium on Times Series Prediction

Neurocomputing
A novel weighted ensemble technique for time series forecasting

PAKDD'12 Proceedings of the 16th Pacific-Asia conference on Advances in Knowledge Discovery and Data Mining - Volume Part I
A fuzzy evolutionary framework for combining ensembles

Applied Soft Computing
Models of performance of time series forecasters

Neurocomputing
MetaStream: A meta-learning based method for periodic algorithm selection in time-changing data

Neurocomputing
Hybridization of Artificial Neural Network and Particle Swarm Optimization Methods for Time Series Forecasting

International Journal of Applied Evolutionary Computation

Quantified Score

Hi-index	0.01

Visualization

Abstract

In research of time series forecasting, a lot of uncertainty is still related to the task of selecting an appropriate forecasting method for a problem. It is not only the individual algorithms that are available in great quantities; combination approaches have been equally popular in the last decades. Alone the question of whether to choose the most promising individual method or a combination is not straightforward to answer. Usually, expert knowledge is needed to make an informed decision, however, in many cases this is not feasible due to lack of resources like time, money and manpower. This work identifies an extensive feature set describing both the time series and the pool of individual forecasting methods. The applicability of different meta-learning approaches are investigated, first to gain knowledge on which model works best in which situation, later to improve forecasting performance. Results show the superiority of a ranking-based combination of methods over simple model selection approaches.