Guinness Partnership: Predictive Insights From Ivy to Damp and Mould

The Challenge

Chris Haynes, Head of Customer Insight at The Guinness Partnership, had worked in similar roles at Eurostar and NatWest before joining the housing association six years ago. He faced a familiar problem: large amounts of unquantified customer comments from surveys, complaints, and contact centres with no objective way to group or score them.

"Without any way of grouping them, scoring them, the only real option is to read them through, which doesn't really give you objectivity," Chris explains. "You'll inevitably remember comments that correspond with whatever you were interested in that day."

Basic attempts at analysis fell short. "Counting the words and creating a word cloud that shows people mention 'Guinness', 'repair', and 'flat' a lot doesn't really tell us anything."

The team needed a way to process comments objectively, trend data over time, and discover issues they might never have considered before.

The Solution

Wordnerds provided the objective analysis framework Chris needed, with practical applications across multiple use cases.

The team now pushes outstanding complaint descriptions through Wordnerds to identify sentiments and red-flag topics like vulnerability and health and safety issues. This creates an objective priority list for teams to work through, rather than making manual judgment calls on which cases to tackle first.

For the assets optimisation team, Chris analysed the frequency customers mentioned different building components—brickwork, windows, doors—along with associated sentiment and volume. This exposed the building-focused team to customer data that complemented their asset-based information.

The Micro-Issue Discovery

But the most interesting application came from identifying issues the team had never thought of before.

"We had a couple of comments from customers when they felt that ivy and creeping plants were blocking ventilation on the exterior of their property, and it was their belief that that was causing damp problems," Chris recalls.

He used Wordnerds to create a botanical topic capturing all possible plant references, then identified every comment mentioning these plants—whether damp was mentioned or not—and cross-referenced it against their damp and mould data.

"We were able to demonstrate that there was a higher incidence of damp and mould if that topic had been triggered by the customer. That was really useful and it allowed me to turn a sort of loose hypothesis into something which was a bit more data-led."

The Strategic Shift

This discovery represents Chris's broader strategy: moving the organisation from backward-facing monthly reporting to predictive approaches. The team is building models looking at likelihood of tenancy failure and unreported damp and mould.

"What I'm interested in is more predictive approaches to data," Chris notes. "I want to use Wordnerds to take each of those themes and see the connection between those themes and whether the customer is satisfied or not."