LONDON (IT BOLTWISE) – A new fraud detection method could help banks significantly reduce the cost of investigating false positives. The startup Haiqu has developed a technique that makes it possible to process high-dimensional data more efficiently and thus better detect subtle financial anomalies.
Today’s daily deals at Amazon! ˗ˋˏ$ˎˊ˗
The startup Haiqu recently presented results from an experiment showing that current quantum computers are able to detect subtle financial anomalies more efficiently than purely classical systems. This research, using a hybrid approach of quantum processing and traditional machine learning models, suggests performance improvements that provide a near-term path to achieving so-called “quantum advantage” for large-scale, real-world problems.
Processing high-dimensional data such as those found in financial transactions presents a significant challenge for conventional machine learning models. This data often includes hundreds or thousands of features that describe each transaction. The challenge is recognizing the subtle, complex patterns that could indicate sophisticated fraud schemes. Haiqu has developed a proprietary data encoding technique that allows over 500 classical features to be encoded into just 128 qubits.
This technique uses the unique properties of quantum mechanics, such as superposition and entanglement, to transform the transaction data into a complex quantum state. This process aims to make the hidden, non-linear relationships and correlations between these hundreds of features more visible, allowing the downstream classical classifier to detect, with superior accuracy and speed, the rare fraudulent anomalies that classical models may miss.
Haiqu’s results show that the quantum-assisted method achieved an F1 score of 0.98 in ideal simulation conditions, which significantly exceeds the classical baseline values of 0.90 to 0.93. Even when running on the real IBM Quantum Heron processor, which introduces noise compared to simulation, the model maintained an F1 score of 0.96, demonstrating its robustness under realistic device conditions.
These advances mark a turning point for quantum machine learning by making complex, high-dimensional data practical at scale. This accelerates the transition to real-world impact in industries like finance, where precision and insight are redefining what is possible. The ability to reduce false positives that place unnecessary strain on fraud investigation teams provides a massive operational advantage to financial institutions due to the cost of these investigations.
Order an Amazon credit card without an annual fee with a credit limit of 2,000 euros!
Bestseller No. 1 ᵃ⤻ᶻ “KI Gadgets”
Bestseller No. 2 ᵃ⤻ᶻ “KI Gadgets”
Bestseller No. 3 ᵃ⤻ᶻ “KI Gadgets”
Bestseller No. 4 ᵃ⤻ᶻ “KI Gadgets”
Bestseller No. 5 ᵃ⤻ᶻ “KI Gadgets”
Please send any additions and information to the editorial team by email to de-info[at]it-boltwise.de. Since we cannot rule out AI hallucinations, which rarely occur with AI-generated news and content, we ask you to contact us via email and inform us in the event of false statements or misinformation. Please don’t forget to include the article headline in the email: “Quantum computing: advances in fraud detection”.