Application of machine learning in predicting fruit waste in a South African fresh produce wholesale market

Machine learning has been generally used for prediction and classification tasks in the food value chain. However, its application in the study of food waste has been limited. Therefore, this study explored the potential of predicting fruit waste at a wholesale level of the food value chain, using a...

Full description

Saved in:
Bibliographic Details
Main Authors: Ikechukwu Kingsley Opara, Douglas Chinenye Divine, Yardjouma Silue, Umezuruike Linus Opara, Jude A. Okolie, Olaniyi Amos Fawole
Format: Article
Language:English
Published: Elsevier 2025-08-01
Series:Journal of Agriculture and Food Research
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2666154325004338
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850072285600284672
author Ikechukwu Kingsley Opara
Douglas Chinenye Divine
Yardjouma Silue
Umezuruike Linus Opara
Jude A. Okolie
Olaniyi Amos Fawole
author_facet Ikechukwu Kingsley Opara
Douglas Chinenye Divine
Yardjouma Silue
Umezuruike Linus Opara
Jude A. Okolie
Olaniyi Amos Fawole
author_sort Ikechukwu Kingsley Opara
collection DOAJ
description Machine learning has been generally used for prediction and classification tasks in the food value chain. However, its application in the study of food waste has been limited. Therefore, this study explored the potential of predicting fruit waste at a wholesale level of the food value chain, using a fresh produce wholesale market in South Africa as a case study. The study aimed to develop a machine learning model to predict fruit waste during marketing. Using historical data at the case study market from 2021 to 2023, different machine learning algorithms such as Random Forest, Gradient boosting, Decision tree, XGBoost, Extra tree and a Stacked Model were applied. The results revealed that fruits in the category of melons and citrus contributed more to fruit waste at the market, while the most waste was during spring and summer seasons, with the highest waste occurring in 2022. The decision tree and extra tree models were the most promising among the machine learning models in the training dataset, with an MAE of 112.19 each. At the same time, the XGBoost outperformed other models for the testing dataset with an MAE of 232.32. The study provided a solid baseline for future studies in this area and recommended integrating varied data for a more robust and accurate model. With further research and implementation, the developed machine learning model has the potential to aid market decisions and policymaking to reduce postharvest waste of fruits at the market, thereby enhancing profitability and sustainability.
format Article
id doaj-art-ed63f3a53dfe4db9ab95fe3cdfe7a893
institution DOAJ
issn 2666-1543
language English
publishDate 2025-08-01
publisher Elsevier
record_format Article
series Journal of Agriculture and Food Research
spelling doaj-art-ed63f3a53dfe4db9ab95fe3cdfe7a8932025-08-20T02:47:06ZengElsevierJournal of Agriculture and Food Research2666-15432025-08-012210206210.1016/j.jafr.2025.102062Application of machine learning in predicting fruit waste in a South African fresh produce wholesale marketIkechukwu Kingsley Opara0Douglas Chinenye Divine1Yardjouma Silue2Umezuruike Linus Opara3Jude A. Okolie4Olaniyi Amos Fawole5SARChI Postharvest Technology Research Laboratory, Africa Institute for Postharvest Technology, Faculty of AgriSciences, Stellenbosch University, Stellenbosch, 7600, South Africa; Department of Food Science, Stellenbosch University, Stellenbosch, 7600, South AfricaDepartment of Process Engineering and Energy Technology, Hochschule Bremerhaven, GermanySouth African Research Chairs Initiative in Sustainable Preservation and Agroprocessing Research, Postharvest and Agroprocessing Research, University of Johannesburg, Auckland Park, Johannesburg, 2006, South Africa; Postharvest and Agroprocessing Research Centre, Department of Botany and Plant Biotechnology, University of Johannesburg, Johannesburg, 2006, South AfricaSARChI Postharvest Technology Research Laboratory, Africa Institute for Postharvest Technology, Faculty of AgriSciences, Stellenbosch University, Stellenbosch, 7600, South Africa; UNESCO International Centre for Biotechnology, Nsukka, 410001, Enugu State, NigeriaGallogly College of Engineering, University of Oklahoma, Norman, OK, 73019, USASouth African Research Chairs Initiative in Sustainable Preservation and Agroprocessing Research, Postharvest and Agroprocessing Research, University of Johannesburg, Auckland Park, Johannesburg, 2006, South Africa; Postharvest and Agroprocessing Research Centre, Department of Botany and Plant Biotechnology, University of Johannesburg, Johannesburg, 2006, South Africa; Corresponding author. South African Research Chairs Initiative in Sustainable Preservation and Agroprocessing Research, Postharvest and Agroprocessing Research, University of Johannesburg, Auckland Park, Johannesburg, 2006, South Africa.Machine learning has been generally used for prediction and classification tasks in the food value chain. However, its application in the study of food waste has been limited. Therefore, this study explored the potential of predicting fruit waste at a wholesale level of the food value chain, using a fresh produce wholesale market in South Africa as a case study. The study aimed to develop a machine learning model to predict fruit waste during marketing. Using historical data at the case study market from 2021 to 2023, different machine learning algorithms such as Random Forest, Gradient boosting, Decision tree, XGBoost, Extra tree and a Stacked Model were applied. The results revealed that fruits in the category of melons and citrus contributed more to fruit waste at the market, while the most waste was during spring and summer seasons, with the highest waste occurring in 2022. The decision tree and extra tree models were the most promising among the machine learning models in the training dataset, with an MAE of 112.19 each. At the same time, the XGBoost outperformed other models for the testing dataset with an MAE of 232.32. The study provided a solid baseline for future studies in this area and recommended integrating varied data for a more robust and accurate model. With further research and implementation, the developed machine learning model has the potential to aid market decisions and policymaking to reduce postharvest waste of fruits at the market, thereby enhancing profitability and sustainability.http://www.sciencedirect.com/science/article/pii/S2666154325004338Machine learningFruit wasteWholesale marketPredictionFood value chain
spellingShingle Ikechukwu Kingsley Opara
Douglas Chinenye Divine
Yardjouma Silue
Umezuruike Linus Opara
Jude A. Okolie
Olaniyi Amos Fawole
Application of machine learning in predicting fruit waste in a South African fresh produce wholesale market
Journal of Agriculture and Food Research
Machine learning
Fruit waste
Wholesale market
Prediction
Food value chain
title Application of machine learning in predicting fruit waste in a South African fresh produce wholesale market
title_full Application of machine learning in predicting fruit waste in a South African fresh produce wholesale market
title_fullStr Application of machine learning in predicting fruit waste in a South African fresh produce wholesale market
title_full_unstemmed Application of machine learning in predicting fruit waste in a South African fresh produce wholesale market
title_short Application of machine learning in predicting fruit waste in a South African fresh produce wholesale market
title_sort application of machine learning in predicting fruit waste in a south african fresh produce wholesale market
topic Machine learning
Fruit waste
Wholesale market
Prediction
Food value chain
url http://www.sciencedirect.com/science/article/pii/S2666154325004338
work_keys_str_mv AT ikechukwukingsleyopara applicationofmachinelearninginpredictingfruitwasteinasouthafricanfreshproducewholesalemarket
AT douglaschinenyedivine applicationofmachinelearninginpredictingfruitwasteinasouthafricanfreshproducewholesalemarket
AT yardjoumasilue applicationofmachinelearninginpredictingfruitwasteinasouthafricanfreshproducewholesalemarket
AT umezuruikelinusopara applicationofmachinelearninginpredictingfruitwasteinasouthafricanfreshproducewholesalemarket
AT judeaokolie applicationofmachinelearninginpredictingfruitwasteinasouthafricanfreshproducewholesalemarket
AT olaniyiamosfawole applicationofmachinelearninginpredictingfruitwasteinasouthafricanfreshproducewholesalemarket