A modal symbolic classifier for selecting time series models

Authors:
Ricardo B. C. Prudêncio;Teresa B. Ludermir;Francisco de A. T. de Carvalho
Affiliations:
Centro de Informática, Universidade Federal de Pernambuco, Caixa Postal 7851, CEP 50732-970, Recife (PE), Brazil;Centro de Informática, Universidade Federal de Pernambuco, Caixa Postal 7851, CEP 50732-970, Recife (PE), Brazil;Centro de Informática, Universidade Federal de Pernambuco, Caixa Postal 7851, CEP 50732-970, Recife (PE), Brazil
Venue:
Pattern Recognition Letters
Year:
2004

Citing 10
Cited 10

Evaluation of aggregate and individual forecast method selection rules

Management Science
C4.5: programs for machine learning

C4.5: programs for machine learning
Rule-based forecasting: development and validation of an expert systems approach to combining time series extrapolations

Management Science
Neural network system for forecasting method selection

Decision Support Systems
Wrappers for feature subset selection

Artificial Intelligence - Special issue on relevance
Data mining: practical machine learning tools and techniques with Java implementations

Data mining: practical machine learning tools and techniques with Java implementations
Expert Systems and Applied Artificial Intelligence

Expert Systems and Applied Artificial Intelligence
Time Series Analysis, Forecasting and Control

Time Series Analysis, Forecasting and Control
Speeding up Recommender Systems with Meta-prototypes

SBIA '02 Proceedings of the 16th Brazilian Symposium on Artificial Intelligence: Advances in Artificial Intelligence
Selecting and ranking time series models using the NOEMON approach

ICANN/ICONIP'03 Proceedings of the 2003 joint international conference on Artificial neural networks and neural information processing

Image compression based on a family of stochastic models

Signal Processing
Selective generation of training examples in active meta-learning

International Journal of Hybrid Intelligent Systems - HIS 2007
Predicting the Performance of Learning Algorithms Using Support Vector Machines as Meta-regressors

ICANN '08 Proceedings of the 18th international conference on Artificial Neural Networks, Part I
Neural network based temporal feature models for short-term railway passenger demand forecasting

Expert Systems with Applications: An International Journal
Time series: Empirical characterization and artificial neural network-based selection of forecasting techniques

Intelligent Data Analysis
An Analysis of Meta-learning Techniques for Ranking Clustering Algorithms Applied to Artificial Data

ICANN '09 Proceedings of the 19th International Conference on Artificial Neural Networks: Part I
Active learning to support the generation of meta-examples

ICANN'07 Proceedings of the 17th international conference on Artificial neural networks
A modal symbolic classifier for interval data

ICONIP'06 Proceedings of the 13th international conference on Neural Information Processing - Volume Part II
A machine learning approach to define weights for linear combination of forecasts

ICANN'06 Proceedings of the 16th international conference on Artificial Neural Networks - Volume Part I
Forecasting model selection through out-of-sample rolling horizon weighted errors

Expert Systems with Applications: An International Journal

Quantified Score

Hi-index	0.10

Visualization

Abstract

The selection of a good model for forecasting a time series is a task that involves experience and knowledge. Employing machine learning algorithms is a promising approach to acquiring knowledge in regards to this task. A supervised classification method originating from the symbolic data analysis field is proposed for the model selection problem. This method was applied in the task of selecting between two widespread models, and compared to other learning algorithms. To date, it has obtained the lowest classification errors among all the tested algorithms.