Retail Fresh

Det ble anslått at 1,05 milliarder tonn mat ble kastet i 2022 totalt. Dette genererer 5-6 prosent av de globale klimagassutslippene. Ferske matvarer (bakevarer, frukt og grønnsaker, varm mat, kjøtt, fisk og delikatesser) utgjør en betydelig del av dette matsvinnet. Ved å forberede riktig mengde mat til ulike kundegrupper må det tas hensyn til store variasjoner i etterspørsel, usikkerhet i lagerbeholdning og varierende holdbarhetstider. Dette gjør det utfordrende å redusere svinn. Ved å bruke avanserte maskinlæringsmetoder har prosjektet som mål å minimere svinnet av ferske varer samtidig som salget opprettholdes. Vi fokuserer også på å forbedre lagerstyringen av ferske produkter som en del av denne prosessen.

For 2019, food waste specifically amounted to 931 million tonnes of food, of which 13% occurred at retailers. The Norwegian Institute for Sustainability Research calculates that largest waste categories in Norwegian grocery trade in 2019 were (in descending order) fresh baked goods (9.9% of economic value), fresh fruit (4.5%), fresh fish (4.5%), vegetables (4.3%) and fresh meat (2.9%). Dry goods represented only 0.5%. While there has been a total reduction of 14% of tons of food wasted in retail stores from 2015-2019, waste of fresh baked goods and fruit and vegetables has changed little during this period. The rapid deterioration rate of fresh produce gives it short and variable shelf life. Therefore, fresh produce is typically not supported by automated goods supply systems. Manual ordering has to take into account the large demand variations, high sales volume and particular high-quality product requirements, which in turn may explain the high degree of waste for fresh produce. To reach the UN Sustainable Development Goal target of 50% reduction in tons of food waste by 2030, retailers must implement waste reduction measures for fresh produce that are much more efficient that the state-of-the-art. Link Retail AS specializes in using data analysis, advanced calculations, and scientific methods to help retailers improve their results. In the project, Link Retail and the University of Bergen will develop a scalable system based on machine learning to minimize wastage of fresh goods while sustaining sales. The software will be tested iteratively on different categories (bread, fruit and vegetables, and then meat, fish and deli) in close collaboration with Meny.