An Ensemble ML Model to Predict the Wastage of Food: Towards Achieving the Food Sustainability

Food waste is a major issue in students' hostel or dormitories, where uneaten food often ends up in the garbage, resulting in economic losses as well as reducing the food sus-tainability. Although Machine Leaning (ML) has emerged as a promising tool for predicting future events in several files, but a very few has been focused to generate accurate predictions and reducing food waste by analyzing read data for a particular context or a country. Therefore, the objective of this research is to explore the factors of affecting food waste in students' hostel or dormitories and to develop an ensemble ML-based food waste prediction system for the student hostel or dormitories. In order to attain these objectives, this study firstly find out the 18 key features that ensure a comprehensive understanding of food waste patterns; then collected the data against these features over the last six months from various mess records of a students' hostel of an engineering university situated in Dhaka, Bangladesh. Secondly, six classification models were developed and analyzed their results and found that Random Forest and Decision Tree performed best accurate prediction (75.41%). Thirdly, the all possible combinations of the studies ML models were explored to find out the best possible ensemble combination; as such, the proposed ensemble ML model showed the highest F1-score of 86.88% that considers the Random Forest and AdaBoost; while all other possible combinations showed around 80–82% F1-score. This research thus contributes to the broader goal of reducing food waste and promoting sustainability in students' mess and other food service settings; as well as may assist the management team in making data-driven decisions about food production, purchasing, and resource allocation.