Loading

Home

/

Case Studies

/

Company Background

The client is a publicly listed Australian utility company involved in the generation and retailing of electricity and gas for residential and commercial use. The company operates a significant generation capacity of 10,984 MW, with 85% of this capacity derived from coal-fired plants. This dual-role as both generator and retailer places the company in a unique position within the market, necessitating robust and efficient management of both operational and customer-facing activities.

Problem Statement

The company faced multiple challenges impacting its operations and customer service:

Debt Management

  • A significant portion of customers were unable to make timely payments for their energy usage, leading to increased debt. This non-payment resulted in financial strain, causing revenue losses due to bad debt.

Data Management

  • The existing data management systems were siloed and inefficient. The need to streamline and centralise data processing was critical to improve decision-making, forecasting, and operational efficiency.

Operational Efficiency

  • The disparate data systems and lack of centralised data storage led to inefficiencies in handling operational data critical for market settlements and metering decisions.

Machine Learning Integration

  • Existing ML models were used in isolation, lacking integration and streamlining, thus reducing their effectiveness in improving business operations.

Solution

To address these challenges, a comprehensive solution was implemented leveraging advanced data management and machine learning technologies:


  • Centralised Data Platform
    • Data Integration:

      Created a centralised data lake using Azure Storage and Databricks to aggregate data from multiple source systems.

    • Streaming Framework:

      Implemented a Spark streaming framework to handle data ingestion, ensuring real-time data availability for critical operational reports.

    • Data Layers:

      Organised data into different layers (staging, raw, integrated, and transformed) for efficient processing and retrieval.

    • ML Platform:

      Established an enterprise ML platform with a feature store accessible to all ML engineers and data scientists, minimising feature duplication and fostering collaboration.

  • Early Debt Detection with AI/ML
    • AI/ML Models:

      Utilised machine learning algorithms to predict customers with a high propensity to fall into debt, based on transactional and behavioral data from the ERP system.

    • Data Privacy Compliance:

      The solution was hosted within the company’s environment to comply with stringent data privacy policies.

    • Causal Analysis:

      Conducted thorough causal analysis to understand the underlying factors leading to debt, enabling targeted interventions.

    • Specialist Teams:

      Formed specialist teams to investigate and address potential issues identified by the AI/ML models, such as billing errors or faulty meters.

  • Operational Improvements
    • Performance Optimisation:

      Leveraged Databricks' optimisation features such as adaptive query execution and dynamic partition pruning to enhance processing speed and resource utilisation.

    • Data Governance:

      Implemented centralised data governance using Databricks Unity Catalog and Collibra to ensure compliance and data integrity.

    • MLOps Integration:

      Developed end-to-end MLOps pipelines using Databricks and Azure DevOps to automate model deployment and monitoring.

Benefits

The implementation of these solutions yielded significant business outcomes:

67%

Debt Reduction

$135 Million

Revenue Realisation

  1. Debt Reduction:
    • Achieved a 67% precision in predicting potential bad debts, leading to a potential revenue realisation of $135 million by preventing customer debt.

  2. Operational Efficiency:
    • Streamlined data processing and reduced compute costs through optimised data management and processing frameworks, delivering near real-time data availability.

  3. Cost Savings:
    • Reduced storage costs by efficiently managing vast amounts of historical data without purging, using cost-effective storage solutions.

  4. Enhanced Decision-Making:
    • Provided a single source of truth for business forecasting and analytical reporting, improving decision-making processes.

  5. Improved Customer Experience:
    • Proactively addressed customer issues related to billing and metering, enhancing overall customer satisfaction.

Technology Levers



Schedule a Call

Please include "@" in the email address.

X

Ready to grow your business? We are. Lets Talk

+61 37018 7620
[email protected]