A Forecasting Methodology Using Support Vector Regression and Dynamic Feature Selection
Authors:
- 1 December 2006
- journal article
- research article
- Published by World Scientific Pub Co Pte Ltd in Journal of Information & Knowledge Management
- Vol. 05 (04) , 329-335
Abstract
Various techniques have been proposed to forecast a given time series. Models from the ARIMA family have been successfully used, as well as regression approaches based on e.g. linear, non-linear regression, neural networks, and Support Vector Regression. What makes the difference in many real-world applications, however, is not the technique but an appropriate forecasting methodology. Here, we propose such a methodology for the regression-based forecasting approach. A hybrid system is presented that iteratively selects the most relevant features and constructs the regression model optimizing its parameters dynamically. We develop a particular technique for feature selection as well as for model construction. The methodology, however, is a generic one providing the opportunity to employ alternative approaches within our framework. The application to several time series underlines its usefulness.Keywords
This publication has 7 references indexed in Scilit:
- Improved supply chain management based on hybrid demand forecastsApplied Soft Computing, 2007
- Multiple Model Regression EstimationIEEE Transactions on Neural Networks, 2005
- Linear Penalization Support Vector Machines for Feature SelectionLecture Notes in Computer Science, 2005
- Practical selection of SVM parameters and noise estimation for SVM regressionNeural Networks, 2004
- Wrappers for feature subset selectionArtificial Intelligence, 1997
- Data preprocessing and intelligent data analysisIntelligent Data Analysis: An International Journal, 1997
- The Nature of Statistical Learning Theory1995