Decision augmentation tools for smarter decisions

Smart meter data, customer data, and more – energy clients are the envy of most industries. And yet, low retention, high churn, and soaring acquisition costs create complex choices for utilities. Sourse provides decision support tools for business decision makers and prebuilt AI models for churn, yield, retention, and acquisition that are powered by rich data.

Discover the difference data makes

Reduction in churn

Predict churn and churn drivers, then automate for real time management.

Increase in LTV

Understand and improve tenure using dynamic clustering and uplift modelling.

Improvement in yield

Experiment and optimise all your cross sell, upsell, and loyalty strategies.

AI trained on energy data

Sourse’s AI models use the unique data available to energy providers, along with competitive data collected over multiple years. These models are developed to enhance customer lifecycle, optimise acquisition and cost to acquire by leveraging retention and yield indicators , and improve customer lifetime value. With accelerated data ingestion and ecosystem connectors, the path to a guaranteed 90% accurate prediction is <60 days.

Pricing and competitive market insights

Multi-year history of front book pricing, back book pricing, and competitive insights across electricity and gas in the Australian region. Competitiveness ranked and engineered into acquisition, retention, and churn models.

Forecasting and anomaly detection

AI is applied to learn complex, over-time trends, and seasonal changes to predict future business performance across all KPIs and all product and / or audience types. The application of AI allows real-time forecasting and up-to-the-minute prediction on whether KPIs will be achieved.

Predictive insights across all KPIs

KPI insights are explained at a population level to provide strategic insights across acquisition, retention, and churn. Each model is explained in the context of revenue and opportunity, causes or reasons, and customer clusters that can be targeted.

Experimentation workbench

Small-scale testing to validate AI insights and treatments to improve the probability of success. Experiments can be easily run through a client’s digital channels to elicit a statistically reliable prediction of success before committing to budgets and resources to deploy large-scale treatments or optimisations.

Always on optimisation

Automated management of a KPI so that many strategies can be simultaneously ‘on.’ The application of AI allows self-learning, meaning continuous improvement is automated. Uplift modelling is applied for maximum impact.


Prebuilt connectors with major cloud ecosystem vendors to automate experiments and optimisations.

  • 47% reduction in churn over 18 months

    “I didn’t believe it was possible to have this much impact on churn”

    – Leading Australian MVNO

  • +50% increase in tenure

    “With an average tenure of 23 months, our prepaid base looked more like a post-paid base.”

    – Australian MVNO

  • +1 products per customer held by 49% of customers

    “Massive impact to the bottom line.”

    – Australian MVNO

Contact us

Want to find out more about how we can help your business drive better decisions and move the needle on the key KPIs?

Contact us