<?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="2026-06-03T15:52:43Z" ns1:href="http://gtr.ukri.org/gtr/api/projects/0C25E6EC-3FC7-41F9-801E-CB652C289523" ns1:id="0C25E6EC-3FC7-41F9-801E-CB652C289523"><ns1:links><ns1:link ns1:href="http://gtr.ukri.org/gtr/api/persons/D565886E-E1F3-4D36-954D-BC98B63634B5" ns1:rel="PM_PER"/><ns1:link ns1:href="http://gtr.ukri.org/gtr/api/organisations/49A90A3B-1F05-4C6F-8507-1A2368351569" ns1:rel="LEAD_ORG"/><ns1:link ns1:href="http://gtr.ukri.org/gtr/api/organisations/49A90A3B-1F05-4C6F-8507-1A2368351569" ns1:rel="PARTICIPANT_ORG"/><ns1:link ns1:end="2025-02-28T00:00:00Z" ns1:href="http://gtr.ukri.org/gtr/api/funds/61043BE8-26BA-4ED6-AE07-26DF2BE06ABF" ns1:rel="FUND" ns1:start="2024-04-30T23:00:00Z"/></ns1:links><ns2:identifiers><ns2:identifier ns2:type="RCUK">10104400</ns2:identifier></ns2:identifiers><ns2:title>AI Insight to Impact in Retail</ns2:title><ns2:status>Closed</ns2:status><ns2:grantCategory>Launchpad</ns2:grantCategory><ns2:leadFunder>Innovate UK</ns2:leadFunder><ns2:abstractText>This project brings four strands of innovation together to create a new Wordnerds product, allowing us to solve specific challenges for verticals while scaling beyond them:

1. AI - Testing, benchmarking and applying the best LLM technology to pre-train models bespoke to individual sectors
2. Software engineering - Building a user interface that supports and automates an intuitive journey from insight to impact
3. Specialist frameworks - Working with sector specialists to understand, build and apply robust impact frameworks, which allow customers in that sector to rapidly prioritise and act on feedback
4. Data - Sourcing/integrating new data streams to address sectoral concerns, for example location-based reviews

The motivation for this project is a significant need in the retail sector, combined with a gap in available technology. Recently Wilko, Paperchase, M&amp;amp;Co all ceased trading, and retail sales fell to a two-year low. Two questions plague the sector:

1. How do we get people back to the high street?
2. How do large organisations balance online and high street offerings, so that one doesn't cannibalise the other?

Wordnerds has been at the forefront of customer understanding since our inception in 2017\. We were among the first commercial products to use Large Language Models (LLMs) to analyse customer feedback. Uniquely, we combined this analysis with Corpus Linguistics to uncover actionable insight.

We conducted a horizon scanning exercise alongside the National Engineering Laboratory to examine the use of LLMs, and found that current classification technology struggles with complex ideas such as behavioural signals.

A new type of AI product is needed, able to understand customer behaviour and differentiate in-person and online experience. But Wordnerds cannot simply pivot to such a product - we must support our other customers, and our ambitions stretch beyond retail. To become a North-East-based global success story, committing to a single sector, however large, will limit us.

If this challenge could be met, it would represent a leap forward in customer service, and in data-driven decision making. Retailers would understand customer behaviour, and remove barriers to reviving town centres.

Wordnerds has had demonstrable success in the creation and commercialisation of NLP innovation over six years. We will build on this in-house capability to deliver all work packages for this project, adding one new, permanent role to the existing team.</ns2:abstractText></ns2:project>