Forecasting Agricultural Commodity Prices Using Model Selection Framework With Time Series Features and Forecast Horizons

• Published in: IEEE access Vol. 8; pp. 28197 - 28209
• Main Authors: Zhang, Dabin, Chen, Shanying, Liwen, Ling, Xia, Qiang
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2020; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Agricultural commodities; agricultural commodity; Agricultural production; Artificial neural networks; Commodities; Decision trees; Economic forecasting; Feature extraction; forecast horizons; Forecasting; Learning theory; Machine learning; Mathematical models; Model selection; Performance enhancement; Predictive models; price forecasting; Pricing; Redundancy; Support vector machines; Task analysis; Time series; Time series analysis; time series features
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2020.2971591

The fluctuations of agricultural commodity prices have a great impact on people's daily lives as well as the inputs and outputs of agricultural production. An accurate forecast of commodity prices is therefore essential if agricultural authorities are to make scientific decisions. To forecast prices more adaptively, this study proposes a novel model selection framework which includes time series features and forecast horizons. Twenty-nine features are used to depict agricultural commodity prices and three intelligent models are specified as the candidate forecast models; namely, artificial neural network (ANN), support vector regression (SVR), and extreme learning machine (ELM). Both random forest (RF) and support vector machine (SVM) are applied to learn the underlying relationships between the features and the performances of the candidate models. Additionally, a minimum redundancy and maximum relevance approach (MRMR) is employed to reduce feature redundancy and further improve the forecast accuracy. The experimental results demonstrate that, firstly, the proposed model selection framework has a better forecast performance compared with the optimal candidate model and simple model average; secondly, feature reduction is a workable approach to further improve the performance of the model selection framework; and thirdly, for bean and pig grain products, different distributions of the time series features lead to a different selection of the optimal models.