Hybrid modeling approaches for agricultural commodity prices using CEEMDAN and time delay neural networks

Abstract Improving the forecasting accuracy of agricultural commodity prices is critical for many stakeholders namely, farmers, traders, exporters, governments, and all other partners in the price channel, to evade risks and enable appropriate policy interventions. However, the traditional mono-scal...

Full description

Saved in:
Bibliographic Details
Main Authors: Pramit Pandit, Atish Sagar, Bikramjeet Ghose, Moumita Paul, Ozgur Kisi, Dinesh Kumar Vishwakarma, Lamjed Mansour, Krishna Kumar Yadav
Format: Article
Language:English
Published: Nature Portfolio 2024-11-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-024-74503-4
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850196275069190144
author Pramit Pandit
Atish Sagar
Bikramjeet Ghose
Moumita Paul
Ozgur Kisi
Dinesh Kumar Vishwakarma
Lamjed Mansour
Krishna Kumar Yadav
author_facet Pramit Pandit
Atish Sagar
Bikramjeet Ghose
Moumita Paul
Ozgur Kisi
Dinesh Kumar Vishwakarma
Lamjed Mansour
Krishna Kumar Yadav
author_sort Pramit Pandit
collection DOAJ
description Abstract Improving the forecasting accuracy of agricultural commodity prices is critical for many stakeholders namely, farmers, traders, exporters, governments, and all other partners in the price channel, to evade risks and enable appropriate policy interventions. However, the traditional mono-scale smoothing techniques often fail to capture the non-stationary and non-linear features due to their multifarious structure. This study has proposed a CEEMDAN (Complete Ensemble Empirical Mode Decomposition with Adaptive Noise)-TDNN (Time Delay Neural Network) model for forecasting non-linear, non-stationary agricultural price series. This study has evaluated its suitability in comparison with the other three major EMD (Empirical Mode Decomposition) variants (EMD, Ensemble EMD and Complementary Ensemble EMD) and the benchmark (Autoregressive Integrated Moving Average, Non-linear Support Vector Regression, Gradient Boosting Machine, Random Forest and TDNN) models using monthly wholesale prices of major oilseed crops in India. Outcomes from this investigation reflect that the CEEMDAN-TDNN hybrid models have outperformed all other forecasting models on the basis of evaluation metrics under consideration. For the proposed model, an average improvement of RMSE (Root Mean Square Error), Relative RMSE and MAPE (Mean Absolute Percentage Error) values has been observed to be 20.04%, 19.94% and 27.80%, respectively over the other EMD variant-based counterparts and 57.66%, 48.37% and 62.37%, respectively over the other benchmark stochastic and machine learning models. The CEEMD-TDNN and CEEMDAN-TDNN models have demonstrated superior performance in predicting the directional changes of monthly price series compared to other models. Additionally, the accuracy of forecasts generated by all models has been assessed using the Diebold-Mariano test, the Friedman test, and the Taylor diagram. The results confirm that the proposed hybrid model has outperformed the alternative models, providing a distinct advantage.
format Article
id doaj-art-37dbfb846bb843aab9232bd9ed601a37
institution OA Journals
issn 2045-2322
language English
publishDate 2024-11-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-37dbfb846bb843aab9232bd9ed601a372025-08-20T02:13:31ZengNature PortfolioScientific Reports2045-23222024-11-0114111910.1038/s41598-024-74503-4Hybrid modeling approaches for agricultural commodity prices using CEEMDAN and time delay neural networksPramit Pandit0Atish Sagar1Bikramjeet Ghose2Moumita Paul3Ozgur Kisi4Dinesh Kumar Vishwakarma5Lamjed Mansour6Krishna Kumar Yadav7Department of Agricultural Statistics & Computer Application, Rabindra Nath Tagore Agriculture College, Birsa Agricultural UniversityDepartment of Agricultural Engineering, Rabindra Nath Tagore Agriculture College, Birsa Agricultural UniversityDepartment of Agricultural Statistics, Bidhan Chandra Krishi ViswavidyalayaDepartment of Agricultural Statistics, Bidhan Chandra Krishi ViswavidyalayaDepartment of Civil Engineering, University of Applied SciencesDepartment of Irrigation and Drainage Engineering, G. B. Pant University of Agriculture and TechnologyDepartment of Zoology, College of Science, King Saud UniversityDepartment of Environmental Science, Parul Institute of Applied Sciences, Parul UniversityAbstract Improving the forecasting accuracy of agricultural commodity prices is critical for many stakeholders namely, farmers, traders, exporters, governments, and all other partners in the price channel, to evade risks and enable appropriate policy interventions. However, the traditional mono-scale smoothing techniques often fail to capture the non-stationary and non-linear features due to their multifarious structure. This study has proposed a CEEMDAN (Complete Ensemble Empirical Mode Decomposition with Adaptive Noise)-TDNN (Time Delay Neural Network) model for forecasting non-linear, non-stationary agricultural price series. This study has evaluated its suitability in comparison with the other three major EMD (Empirical Mode Decomposition) variants (EMD, Ensemble EMD and Complementary Ensemble EMD) and the benchmark (Autoregressive Integrated Moving Average, Non-linear Support Vector Regression, Gradient Boosting Machine, Random Forest and TDNN) models using monthly wholesale prices of major oilseed crops in India. Outcomes from this investigation reflect that the CEEMDAN-TDNN hybrid models have outperformed all other forecasting models on the basis of evaluation metrics under consideration. For the proposed model, an average improvement of RMSE (Root Mean Square Error), Relative RMSE and MAPE (Mean Absolute Percentage Error) values has been observed to be 20.04%, 19.94% and 27.80%, respectively over the other EMD variant-based counterparts and 57.66%, 48.37% and 62.37%, respectively over the other benchmark stochastic and machine learning models. The CEEMD-TDNN and CEEMDAN-TDNN models have demonstrated superior performance in predicting the directional changes of monthly price series compared to other models. Additionally, the accuracy of forecasts generated by all models has been assessed using the Diebold-Mariano test, the Friedman test, and the Taylor diagram. The results confirm that the proposed hybrid model has outperformed the alternative models, providing a distinct advantage.https://doi.org/10.1038/s41598-024-74503-4Agriculture price forecastingEmpirical mode decompositionIntrinsic mode functionsNon-linearityTime delay neural network
spellingShingle Pramit Pandit
Atish Sagar
Bikramjeet Ghose
Moumita Paul
Ozgur Kisi
Dinesh Kumar Vishwakarma
Lamjed Mansour
Krishna Kumar Yadav
Hybrid modeling approaches for agricultural commodity prices using CEEMDAN and time delay neural networks
Scientific Reports
Agriculture price forecasting
Empirical mode decomposition
Intrinsic mode functions
Non-linearity
Time delay neural network
title Hybrid modeling approaches for agricultural commodity prices using CEEMDAN and time delay neural networks
title_full Hybrid modeling approaches for agricultural commodity prices using CEEMDAN and time delay neural networks
title_fullStr Hybrid modeling approaches for agricultural commodity prices using CEEMDAN and time delay neural networks
title_full_unstemmed Hybrid modeling approaches for agricultural commodity prices using CEEMDAN and time delay neural networks
title_short Hybrid modeling approaches for agricultural commodity prices using CEEMDAN and time delay neural networks
title_sort hybrid modeling approaches for agricultural commodity prices using ceemdan and time delay neural networks
topic Agriculture price forecasting
Empirical mode decomposition
Intrinsic mode functions
Non-linearity
Time delay neural network
url https://doi.org/10.1038/s41598-024-74503-4
work_keys_str_mv AT pramitpandit hybridmodelingapproachesforagriculturalcommoditypricesusingceemdanandtimedelayneuralnetworks
AT atishsagar hybridmodelingapproachesforagriculturalcommoditypricesusingceemdanandtimedelayneuralnetworks
AT bikramjeetghose hybridmodelingapproachesforagriculturalcommoditypricesusingceemdanandtimedelayneuralnetworks
AT moumitapaul hybridmodelingapproachesforagriculturalcommoditypricesusingceemdanandtimedelayneuralnetworks
AT ozgurkisi hybridmodelingapproachesforagriculturalcommoditypricesusingceemdanandtimedelayneuralnetworks
AT dineshkumarvishwakarma hybridmodelingapproachesforagriculturalcommoditypricesusingceemdanandtimedelayneuralnetworks
AT lamjedmansour hybridmodelingapproachesforagriculturalcommoditypricesusingceemdanandtimedelayneuralnetworks
AT krishnakumaryadav hybridmodelingapproachesforagriculturalcommoditypricesusingceemdanandtimedelayneuralnetworks