Archer Moves to Test Quantum Fraud Detection on 280,000 Real Bank Transactions

By

Key Takeaways

Archer Materials Quantum Machine Learning project hits a major milestone with 280,000 bank transaction records prepped for QML fraud detection simulations, targeting initial algorithm results by mid-2026 and a full prototype by year-end.

  • Archer Materials has completed dataset preparation for its Quantum Machine Learning fraud detection project, using over 280,000 bank transaction records sourced from a publicly available dataset previously used in classical ML research.
  • The project entered its QML simulations and benchmarking phase, with initial algorithm performance results expected by mid-2026 and a full QML prototype targeted for end of 2026.
  • Data preprocessing techniques were applied to reduce complexity and ensure compatibility with current quantum hardware constraints, specifically the limited number of qubits available on present-day quantum systems.
  • CEO Dr Simon Ruffell confirmed the project is central to Archer's strategy of broadening commercialisation pathways for its quantum technologies across computing, sensing, and medical diagnostics.

Archer Materials (ASX: AXE) has completed dataset preparation for its quantum machine learning fraud detection project and is now moving into simulations and benchmarking. The company has identified a dataset containing over 280,000 bank transaction records to support development of its QML model, with initial algorithm performance results expected by mid-2026 and a full prototype targeted by year-end.

Archer Materials advances quantum fraud detection project with 280,000-transaction dataset

The Archer Materials Quantum Machine Learning project commenced in January 2026 and focuses on developing QML algorithms to enhance detection of fraudulent activities in financial transactions. With dataset preparation now complete, the company is transitioning to the next phase of QML simulations and benchmarking against traditional machine learning techniques.

The publicly available dataset consists of bank fraud transaction records that have previously been used in classical machine learning research. This enables the team to benchmark quantum approaches against established traditional algorithms. Significant preprocessing work was undertaken to reduce data complexity while preserving key features required for model training, an approach that is standard in both quantum and classical machine learning research.

The limited number of qubits available on present-day quantum systems necessitated these data complexity reduction techniques. Qubits represent quantum information processing power, and current hardware constraints require careful dataset preparation to ensure compatibility with available quantum computing resources.

Initial indications of algorithm performance are expected by mid-2026, providing the basis for a full QML prototype to be ready by the end of 2026. The project forms part of Archer’s broader strategy to explore practical applications of quantum computing in real-world data environments and expand commercialisation pathways for its suite of quantum technologies.

What is quantum machine learning and why does it matter?

Quantum machine learning is an emerging quantum application that uses quantum computing to analyse complex datasets. As quantum hardware develops, QML has the potential to provide faster processing and improved optimisation for certain data analysis tasks compared with classical machine learning techniques.

Key advantages of quantum machine learning:

  • Enhanced processing speed: Potential for faster analysis of large, complex datasets
  • Improved optimisation: Better problem-solving capabilities for specific computational tasks
  • Real-world applications: Particularly suited to problems like financial fraud detection that benefit from advanced pattern recognition
  • Benchmarkable performance: Can be directly compared against traditional machine learning approaches

Financial fraud detection represents an application that could benefit from these quantum approaches. The technology’s development depends on overcoming current hardware limitations, including the restricted number of qubits available on present-day quantum systems.

Dataset preparation and technical approach

The team identified a publicly available dataset of over 280,000 bank transaction records consisting of bank fraud transactions. The dataset’s prior use in classical machine learning research is important, as it ensures benchmarking can be performed against traditional machine learning algorithms.

Given the limited quantum information processing power available on present-day quantum systems, techniques have been applied to reduce data complexity while preserving key features required for model training. This preprocessing work is standard practice in both quantum and classical machine learning research and ensures compatibility with current quantum computing constraints.

Milestone Status Expected Timing
Dataset identification Complete Q3 FY26
Data preprocessing Complete Q3 FY26
QML simulations & benchmarking Underway Mid-2026
Full QML prototype Targeted End of 2026

With dataset preparation completed, the project is transitioning to QML simulations and benchmarking. By mid-year, this work will provide initial indications on algorithm performance for fraud detection.

CEO outlines commercialisation pathway

Dr Simon Ruffell, CEO of Archer Materials, highlighted the project’s progress and strategic significance within the company’s broader quantum technology development programme.

Dr Simon Ruffell, CEO, Archer Materials

“We have made significant progress with the QML fraud detection project. We are now working towards getting the initial results mid-year for a prototype to be ready by the end of this year. The project forms part of Archer’s broader strategy to explore practical applications of quantum computing in real-world data environments. Development of prototypes of QML-based software, through projects like this one, are key to Archer’s development and broadening of commercialisation pathways for the technology.”

The commentary reinforces management’s focus on translating quantum research into practical commercial applications. Development of QML-based software prototypes represents a key pathway for Archer to broaden commercialisation opportunities for its quantum technologies beyond its existing focus areas in computing, sensing, and medical diagnostics.

What to watch for next

The company has outlined two clear near-term milestones for investors to monitor:

  1. Mid-2026: Initial algorithm performance indications for fraud detection
  2. End of 2026: Full QML prototype delivery

The QML fraud detection project sits within Archer’s broader suite of quantum technologies spanning computing, sensing, and medical diagnostics. The company is developing advanced semiconductor devices, including chips relevant to quantum computing applications, and utilises global partnerships to develop these technologies for potential deployment across multiple industries.

Archer continues developing practical quantum applications for real-world commercial use, with the fraud detection project representing one pathway to demonstrate the commercial viability of quantum machine learning approaches in data-intensive business environments.

Want the Next Quantum Tech Breakthrough in Your Inbox?

Join 20,000+ investors getting FREE breaking ASX tech news delivered within minutes of release, complete with in-depth analysis. Click the “Free Alerts” button at Big News Blast to stay ahead on quantum computing, AI, and emerging technology announcements the moment they hit the market.


Share Article:
John Zadeh
By John Zadeh
Founder & CEO
John Zadeh is a seasoned small-cap investor and digital media entrepreneur with over 10 years of experience in Australian equity markets. As Founder and CEO of StockWire X, he leads the platform's mission to level the playing field by delivering real-time ASX announcement analysis and comprehensive investor education to retail and professional investors globally.
Learn More
Most Popular
Get Our "Big News" Alerts
Join 20,000+ subscribers today.

Breaking ASX Alerts Direct to Your Inbox

Join +20,000 subscribers receiving alerts.

Join thousands of investors who rely on StockWire X for timely, accurate market intelligence.

About the Publisher