TIME SERIES PREDICTION COMPETITION

[Amaury Lendasse]

Please post and circulate as you see fit. Thank you.
 
2004 International Joint Conference on Neural Networks
Special session organized in collaboration with the European Neural Network
Society, the Machine Learning Group of the Universite catholique de Louvain
in Belgium and the Neural Networks Research Center of the Helsinki
University of Technology 
       
TIME SERIES PREDICTION COMPETITION
http://www.cis.hut.fi/~lendasse/competition/competition.html
 
The CATS Benchmark
 
The goal of this competition is to provide a new benchmark for the problem
of time series prediction and to compare the different methods or models
that can be used for the prediction.
The proposed time series is the CATS benchmark (for Competition on
Artificial Time Series).
 
This artificial Time Series with 5,000 data is given. Within those 100
values are missing. 
These missing values are divided in 5 blocks:
 
- elements 981 to 1,000;
- elements 1,981 to 2,000;
- elements 2,981 to 3,000;
- elements 3,981 to 4,000;
- elements 4,981 to 5,000;    
 
These 100 missing values have to be predicted.
 
The Mean Square Error E will be computed on the 100 missing values. 
 
The authors are requested to provide their prediction for the 100 missing
values.
The submitted methods will be ranked using this Mean Square Error E.
 
The best papers (according to the quality of the prediction and the quality
of the paper itself) will be selected for the special session that will be
held during IJCNN 2004. Furthermore, a limited number of those papers will
be published in a special issue of an International Scientific Journal.
 
The competition starts on February, 1st 2004 and the deadline for the
submission is March, 7th 2004.
 
Special session organised by Amaury Lendasse, Michel Verleysen, Erkki Oja
and Olli Simula.
 
Dr. Amaury Lendasse
Helsinki University of Technology
Laboratory of Computer and Information Science 
P.O. Box 5400
FIN-02015 HUT
FINLAND
tel. +358-9-451 4499
fax +358-9-451 3277

Email: lendasse at cis.hut.fi
URL:  <http://www.cis.hut.fi/%7Elendasse> http://www.cis.hut.fi/~lendasse