DocumentCode :
2127810
Title :
Evaluation on Forecasting Algorithms of Time Series
Author :
Lang, Rongling ; Lv, Yongle ; Cui, Qunfa
Author_Institution :
Sch. of Electron. & Inf. Eng., Beijing Univ. of Aeronaut. & Astronaut., Beijing, China
fYear :
2009
fDate :
20-22 Sept. 2009
Firstpage :
1
Lastpage :
4
Abstract :
Time series forecasting exists in a lot of fields, and many forecasting algorithms were proposed at present. How to evaluate forecasting algorithm is requested in algorithm analysis. The techniques of evaluation of forecasting are studied here, and a novel measure, relative degree of association, is also proposed to evaluate forecasting algorithm. Some experimental results using these measures give performances of these measures in evaluating forecasting algorithms.
Keywords :
forecasting theory; time series; novel measure; relative degree-of-association; time series forecasting algorithm; Algorithm design and analysis; Data mining; Economic forecasting; Extraterrestrial measurements; Finance; Pattern analysis; Performance evaluation; Root mean square; Time measurement; Time series analysis;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Management and Service Science, 2009. MASS '09. International Conference on
Conference_Location :
Wuhan
Print_ISBN :
978-1-4244-4638-4
Electronic_ISBN :
978-1-4244-4639-1
Type :
conf
DOI :
10.1109/ICMSS.2009.5303080
Filename :
5303080
Link To Document :
بازگشت