We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Prediction of annual rice imports emphasizes on systematic error reduction with smoothing series and optimal parameter selection techniques.
- Authors
Sujjaviriyasup, Thoranin
- Abstract
From an economic perspective, rice is not only a principal staple food for nearly half of the world's population but also a significant commodity in many countries. Consequently, the accuracy of demand uncertainty concerning rice imports, which can be useful information to support critical decision-making on trading and food security management, is very challenging. The proposed model of simple exponential smoothing, support vector regression, and generalized simulated annealing is proposed and developed to predict annual rice imports based on twenty datasets across importer countries. The proposed model takes advantage of both suitable parameter selection and noise reduction in systematic error reduction with smoothing series to achieve more accuracy and precision. The empirical results revealed that the proposed model can improve accuracy based on five accuracy measures and is significantly different from other models at 0.05 significance levels. Moreover, the proposed model can provide consistency and reliability for forecasting rice imports in advance. Consequently, the proposed model can be a promising tool to support decision-making for policymakers.
- Subjects
RICE; SIMULATED annealing; IMPORTS; NOISE control; SECURITIES trading; STATISTICAL smoothing; FOOD industry
- Publication
Neural Computing & Applications, 2024, Vol 36, Issue 19, p11275
- ISSN
0941-0643
- Publication type
Article
- DOI
10.1007/s00521-024-09742-7