Research Article
Overview and Demonstrative Use Case of Quantum Machine Learning in Finance
@INPROCEEDINGS{10.1007/978-3-032-44094-5_11, author={Chau Bao Phung and Bradley D. E. McNiven and Emmanuel Haven and Trung Q. Duong}, title={Overview and Demonstrative Use Case of Quantum Machine Learning in Finance}, proceedings={Industrial Networks and Intelligent Systems. 12th EAI International Conference, INISCOM 2026, Da Nang, Vietnam, February 26--27, 2026, Proceedings}, proceedings_a={INISCOM}, year={2026}, month={11}, keywords={Quantum machine learning financial applications credit scoring fraud detection portfolio optimization time series forecast}, doi={10.1007/978-3-032-44094-5_11} }- Chau Bao Phung
Bradley D. E. McNiven
Emmanuel Haven
Trung Q. Duong
Year: 2026
Overview and Demonstrative Use Case of Quantum Machine Learning in Finance
INISCOM
Springer
DOI: 10.1007/978-3-032-44094-5_11
Abstract
The growing complexity and volume of financial data have posed the challenges of efficiency and accuracy for current classical machine learning. Quantum machine learning (QML) offers a promising alternative by exploiting quantum characteristics to process high-dimensional financial information more efficiently. This paper reviews key QML algorithms, i.e., quantum support vector machines, variational quantum neural networks, and quantum approximate optimization algorithms, and explores their applications in credit scoring, fraud detection, portfolio optimization, and time-series forecasting. Consequently, a high-level framework is proposed for integrating QML into financial institutions, outlining progressive stages from experimentation to infrastructure deployment. The study also explores QML challenges and limitations, including data encoding, hardware noise, and scalability, and discusses potential hybrid quantum–classical solutions for efficient implementation.