Towards modelling SHARP diets, based on nutritional adequacy, sustainability metrics and population diversity parameters
Data Envelopment Analysis-based diet model serves as an elegant tool for optimizing diets in an innovative way. Its generic structure allows for a variety of
extensions to be made on top of the core model. Its common primary objective is diet health optimization, while auxiliary objectives can be diverse, for instance
diet sustainability and preferability. If the appropriate diet sustainability metric is available, its inclusion in the model is relatively straightforward, whereas diet
preferability presents a much more significant challenge. Instead of inferring consumer preferences by computing consumer similarities, as is the case with
some data envelopment analysis-based diet models, our approach is based on food item similarities, which allows for much more intuitive and diverse food
item recommendations, including those for food items that have not been observed in consumers’ diets.