What already exists

Several organisations work on parts of this problem. Each line describes what a public source says, not our assessment of the product.

Horizon Power (WA)

Presented a Hardship Probability Algorithm in May 2023 that rates customers' likelihood of payment default from payment behaviour, so Customer Relationship Officers can reach out early. The AER's Customer Engagement Toolkit (February 2025) includes a Horizon Power case study.

Source

EnergyAustralia (Australia)

Uses internal and external data to proactively identify customers who may be vulnerable. Its EnergyAssist program prevented 53% of vulnerable cases from reaching disconnection in 2025, with 56,668 customers in the program at the end of 2025.

Source

Australian Red Cross Telecross REDi (South Australia)

Volunteers phone registered vulnerable people daily during heatwaves. Climasens, a climate intelligence start-up, provided climate and population risk data in a South Australian pilot, and received a $500,000 Telstra Foundation grant to scale in December 2022.

Source

UK Power Networks PULSE (UK)

A GBP 1,037,000 project (2 March 2026 to 31 December 2027) using smart meter data, with consent, and surveys to spot customers cutting back energy use to lower bills or running out of prepayment credit.

Source

EDF Energy (UK)

In July 2022 described clustering smart prepayment customers' meter and transaction data to find a segment that appeared financially vulnerable, checked against Priority Services Register flags and expert review.

Source

Bidgely (US)

Sells an AI affordability product that identifies households needing bill assistance from consumption data and automates outreach. Won a 2026 Environment + Energy Leader award (April 2026).

Source

Thriving Communities Partnership (Australia)

Its One Stop One Story Hub lets frontline staff refer a customer to several support services at once. It had helped over 850 people since its October 2021 launch, according to WSAA.

Source

Experian Australia

Offers a hardship scoring model based on household segmentation. Area and segment profiling is something our brief warns against, so we treat it as a contrast, not a model.

Source

The gap

In our desk research we did not find a published tool that combines weather forecasts with a household's own billing, usage and contact data to give staff a timed, plain-language reason before an extreme weather event. Utilities may run internal tools that are not public, so we are checking this in every customer conversation.

A project developed through GreenTech Hub's GreenSpark innovation program, Perth, 15 to 30 October 2026.

Team Connect is an independent student and early-career team. Organisations named on these pages are referenced from public sources or our own conversations; naming them does not mean they endorse, partner with or have reviewed this project.

Last updated: 17 October 2026