Forecasting Agricultural Commodity Prices Using Model Selection Framework With Time Series Features and Forecast Horizons
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 p...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2020-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/8981960/ |
id |
doaj-b9093ef10e8c4218afa7ced6ac611284 |
---|---|
record_format |
Article |
spelling |
doaj-b9093ef10e8c4218afa7ced6ac6112842021-03-30T02:19:43ZengIEEEIEEE Access2169-35362020-01-018281972820910.1109/ACCESS.2020.29715918981960Forecasting Agricultural Commodity Prices Using Model Selection Framework With Time Series Features and Forecast HorizonsDabin Zhang0https://orcid.org/0000-0001-9803-9795Shanying Chen1https://orcid.org/0000-0002-4619-6788Ling Liwen2https://orcid.org/0000-0002-4121-3905Qiang Xia3https://orcid.org/0000-0003-2477-1742College of Mathematics and Informatics, South China Agricultural University, Guangdong, ChinaCollege of Mathematics and Informatics, South China Agricultural University, Guangdong, ChinaCollege of Mathematics and Informatics, South China Agricultural University, Guangdong, ChinaCollege of Mathematics and Informatics, South China Agricultural University, Guangdong, ChinaThe 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.https://ieeexplore.ieee.org/document/8981960/Model selectionagricultural commodityprice forecastingtime series featuresforecast horizons |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Dabin Zhang Shanying Chen Ling Liwen Qiang Xia |
spellingShingle |
Dabin Zhang Shanying Chen Ling Liwen Qiang Xia Forecasting Agricultural Commodity Prices Using Model Selection Framework With Time Series Features and Forecast Horizons IEEE Access Model selection agricultural commodity price forecasting time series features forecast horizons |
author_facet |
Dabin Zhang Shanying Chen Ling Liwen Qiang Xia |
author_sort |
Dabin Zhang |
title |
Forecasting Agricultural Commodity Prices Using Model Selection Framework With Time Series Features and Forecast Horizons |
title_short |
Forecasting Agricultural Commodity Prices Using Model Selection Framework With Time Series Features and Forecast Horizons |
title_full |
Forecasting Agricultural Commodity Prices Using Model Selection Framework With Time Series Features and Forecast Horizons |
title_fullStr |
Forecasting Agricultural Commodity Prices Using Model Selection Framework With Time Series Features and Forecast Horizons |
title_full_unstemmed |
Forecasting Agricultural Commodity Prices Using Model Selection Framework With Time Series Features and Forecast Horizons |
title_sort |
forecasting agricultural commodity prices using model selection framework with time series features and forecast horizons |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2020-01-01 |
description |
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. |
topic |
Model selection agricultural commodity price forecasting time series features forecast horizons |
url |
https://ieeexplore.ieee.org/document/8981960/ |
work_keys_str_mv |
AT dabinzhang forecastingagriculturalcommoditypricesusingmodelselectionframeworkwithtimeseriesfeaturesandforecasthorizons AT shanyingchen forecastingagriculturalcommoditypricesusingmodelselectionframeworkwithtimeseriesfeaturesandforecasthorizons AT lingliwen forecastingagriculturalcommoditypricesusingmodelselectionframeworkwithtimeseriesfeaturesandforecasthorizons AT qiangxia forecastingagriculturalcommoditypricesusingmodelselectionframeworkwithtimeseriesfeaturesandforecasthorizons |
_version_ |
1724185450185228288 |