Authors:
Varsha Ramkumar, S. Rubin Bose, J. Angelin Jeba, R. Regin, S. Suman Rajest

Addresses:
Department of Business Analytics, University of Galway, Galway, Ireland. School of Computer Science and Engineering, SRM Institute of Science and Technology, Ramapuram, Chennai, Tamil Nadu, India. Department of Electronics and Communication Engineering, S.A. Engineering College, Chennai, Tamil Nadu, India. Department of Research and Development, Dhaanish Ahmed College of Engineering, Chennai, Tamil Nadu, India.

Abstract:

Food waste has become a serious problem and a loss of resources around the world, and hurts the balance of the environment, with an economic loss. This paper suggests a machine learning-based predictive model, which is hybrid with a quantum-inspired optimization approach, to estimate food waste and the associated economic loss more accurately. The system uses Linear Regression to assess the economic impact, while Random Forest is used to predict waste quantities, both enhanced by quantum optimisation for feature selection and hyperparameter tuning. The proposed architecture not only predicts food waste but also displays alert levels (Low, Moderate, High, and Critical) and provides intelligent suggestions to minimize food waste. Unlike classical models, this hybrid approach results in faster convergence, better generalisation, and more interpretable predictions. The key challenges encountered while developing the model were data imbalance, feature dependency, and fine-tuning the quantum layer with the classical ML pipeline to ensure stable model training and efficient computation. The quantum-enhanced learning approach achieved high predictive accuracy and demonstrated that these techniques can significantly improve decision-making in sustainable food management systems. Overall, the paper emphasizes QML's potential to solve real-world problems, such as food waste, and provides a scalable solution that supports global sustainability goals through data-driven insights, economic forecasting, and actionable alerts for effective food resource management.

Keywords: Resilient Food Chain; Economic Loss; Total Food Waste Prediction; Linear Regression; Random Forest; Ensemble Learning; Non-Linear Relationships; Prediction Accuracy; Quantum Machine Learning.

Received on: 10/05/2025, Revised on: 13/07/2025, Accepted on: 24/09/2025, Published on: 05/06/2026

DOI: 10.69888/FTSESS.2026.000718

FMDB Transactions on Sustainable Environmental Sciences, 2026 Vol. 3 No. 2, Pages: 103-122

• Views : 104
• Downloads : 25

Download PDF