Earticle

초록

영어

To improve the forecasting accuracy of oil prices, this paper has proposed oil price predicting model (PSR-LSSVM) based on unified solving by phase space reconstruction and predicting algorithm parameters using interrelation between phase-space reconstruction and predicting algorithm. The LSSVM is selected as the predicting algorithm of oil prices, and the parameters of phase space reconstruction and LSSVM are taken as individuals of the genetic algorithm, and the optimal delay time, embedding dimension and LSSVM parameters are obtained through selection, crossover and mutation evolutionary mechanism, and finally, the predicting model of oil prices is established and the performance of predicting model is tested by Daqing oil price time series. The results show that the proposed model PSR-LSSVM obtains higher predicting accuracy than the oil-price forecasting models of independently optimized phase-space reconstruction and LSSVM, which provides a new research idea for the predicting problem of chaotic time series.

목차

Abstract
 1. Introduction
 2. Related Research
 3. Phase-Space Reconstruction and LSSVM
  3.1. Phase Space Reconstruction Theory
  3.2. LSSVM
 4. Unified Solving by Parameter of Oil price Forecast Model
  4.1. Individual Coding Design
  4.2. Fitness Function Design
  4.3. Unified solution Procedure of Oil Price Forecast Model Parameter
 5. Simulation Experiment
  5.1. Data Sources
  5.2. Contrast Model and Evaluation Criteria
  5.3. Model Implementation
 6. Conclusion
 Acknowledgments
 References

키워드

저자

• Hu Shuyu [ College of Network Education, Hunan Radio and Television University, Changsha, 410004, China ]
• Huang Ming [ College of Economics and Management, Hunan Radio and Television University, Changsha, 410004, China ] Corresponding Author

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  International Journal of u- and e- Service, Science and Technology

• 간기

  격월간

• pISSN

  2005-4246

• 수록기간

  2008~2016

• 십진분류

  KDC 505 DDC 605