<?xml version="1.0" encoding="UTF-8"?><ns2:project xmlns:ns1="http://gtr.rcuk.ac.uk/gtr/api" xmlns:ns2="http://gtr.rcuk.ac.uk/gtr/api/project" xmlns:ns3="http://gtr.rcuk.ac.uk/gtr/api/fund" xmlns:ns4="http://gtr.rcuk.ac.uk/gtr/api/person" xmlns:ns5="http://gtr.rcuk.ac.uk/gtr/api/project/outcome" xmlns:ns6="http://gtr.rcuk.ac.uk/gtr/api/organisation" ns1:created="2026-06-22T07:57:45Z" ns1:href="http://gtr.ukri.org/gtr/api/projects/A494849F-5666-4ED6-B179-9CB682ADD634" ns1:id="A494849F-5666-4ED6-B179-9CB682ADD634"><ns1:links><ns1:link ns1:href="http://gtr.ukri.org/gtr/api/persons/C8DB94DA-30E8-4839-A98F-EF918689052C" ns1:rel="PM_PER"/><ns1:link ns1:href="http://gtr.ukri.org/gtr/api/organisations/7A9AB09C-8CC2-47C0-ABD8-348DFBDD3E40" ns1:rel="LEAD_ORG"/><ns1:link ns1:href="http://gtr.ukri.org/gtr/api/organisations/7A9AB09C-8CC2-47C0-ABD8-348DFBDD3E40" ns1:rel="PARTICIPANT_ORG"/><ns1:link ns1:end="2026-01-31T00:00:00Z" ns1:href="http://gtr.ukri.org/gtr/api/funds/90E51EDD-29A1-4541-A1DE-CCBF75AE104F" ns1:rel="FUND" ns1:start="2025-05-31T23:00:00Z"/></ns1:links><ns2:identifiers><ns2:identifier ns2:type="RCUK">10157237</ns2:identifier></ns2:identifiers><ns2:title>Developing an AI-driven, human-in-the-loop demand forecasting solution for decentralised fresh food businesses to optimise supply chains, reduce waste, and improve efficiency.</ns2:title><ns2:status>Closed</ns2:status><ns2:grantCategory>Collaborative R&amp;D</ns2:grantCategory><ns2:leadFunder>Innovate UK</ns2:leadFunder><ns2:abstractText>At Martee AI, we're on a mission to solve one of the food-to-go sector's biggest headaches - ensuring that there's always enough fresh food on the shelves without wasting a ton of it in the process. Our existing product uses cutting-edge AI to generate super-accurate demand forecasts, helping businesses to predict precisely how much of each product to make each day. We deliver these forecasts via an easy-to-use API, so businesses can just plug them in and get to work.

The magic behind what we do lies in our centralised learning techniques which combine anonymised data from lots of smaller businesses to train powerful algorithms that can return more accurate forecasts to each of the businesses, thanks to the aggregate predictive power created. Through our approach, even smaller food-to-go businesses can get access to supercharged, enterprise-level forecasting without needing huge amounts of their own data. The result is less waste, better fresh food availability and happier customers.

With this current project, we're taking things to the next level - we want to create a brand-new tool that brings customer service professionals - the people in food businesses who see everything happening on the ground - into the forecasting process. Imagine a simple interface where people working in stores can tag what they notice, like one-off explainable demand spikes or unusual events in the local area, and feed those insights back into forecasting models. Their observations will make our forecasts even smarter and more adaptable to real-world, day-to-day changes which models could not detect without human input.

This project is about more than numbers - it's about creating a more sustainable, efficient, and people-centered future for food-to-go businesses and ultimately for the food sector more widely. With Martee AI, we're proving that AI isn't just for big companies or tech giants - it can be a game-changer for businesses of all sizes and the people who run them every day.</ns2:abstractText></ns2:project>