Evolving Multilevel Forecast Combination Models - An Experimental Study

Created by W.Langdon from gp-bibliography.bib Revision:1.7615

@InProceedings{Riedel:2005:NiSIS,

• author = "Silvia Riedel and Bogdan Gabrys",
• title = "Evolving Multilevel Forecast Combination Models - An Experimental Study",
• booktitle = "First European Symposium on Nature-inspired Smart Information Systems, Workshop on Nature-inspired Data Base Technology, NiSIS 2005",
• year = "2005",
• editor = "Derek Linkens",
• address = "Albufeira, Portugal",
• month = "4-5 " # oct # " 2015",
• keywords = "genetic algorithms, genetic programming, forecast combination, adaptive forecasting, genetic programming airline, revenue management",
• annote = "The Pennsylvania State University CiteSeerX Archives",
• bibsource = "OAI-PMH server at citeseerx.ist.psu.edu",
• language = "en",
• oai = "oai:CiteSeerX.psu:10.1.1.484.8838",
• rights = "Metadata may be used without restrictions as long as the oai identifier remains attached to it.",
• URL = "http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.484.8838",
• URL = "http://www.nisis.risk-technologies.com/msc/papers/A22b_p_RiedelGabrys.pdf",
• URL = "http://www.nisis.risk-technologies.com/msc/PortugalProgrammDraft.aspx",
• size = "10 pages",
• abstract = "This paper provides a description and experimental comparison of different forecast combination techniques for the application of Revenue Management forecasting for Airlines. In order to benefit from the advantages of forecasts predicting seasonal demand using different forecast models on different aggregation levels and to reduce the risks of high noise terms on low level predictions and over generalisation on higher levels, various approaches based on combination of many predictions are presented and experimentally compared. We propose to evolve combination structures dynamically using Evolutionary Computing approaches. The evolved structures are not only able to generate predictions representing well balanced and stable fusions of methods and levels, they are also characterised by high adaptive capabilities. The focus on different levels or methods of forecasting may change as well as the complexity of the combination structure depending on changes in parts of the input data space in different data aggregation levels. Significant forecast improvements have been obtained when using the proposed dynamic multilevel structures.",
• notes = "The Nature-inspired Smart Information Systems project was funded by the European Commission.",

}

Genetic Programming entries for Silvia Riedel Bogdan Gabrys

Citations