This article has been reviewed according to Science X's editorial process and policies. Editors have highlighted the following attributes while ensuring the content's credibility: Selecting profitable investments from an increasingly large and constrained pool of assets could become more effective with a hybrid quantum-classical method, according to research in the International Journal of Information and Communication Technology. The work could help solve a major computational problem in modern portfolio management.
The team's framework, hybrid quantum-classical portfolio optimization (HQCPO), combines two quantum approaches with conventional computing. Quantum annealing searches for promising solutions, while variational quantum algorithms, which adjust parameters iteratively, allow the system to represent more flexible financial constraints. The system also divides the network of related assets into smaller groups, reducing the quantum resources required.
Choosing just a few dozen assets from a pool of 120 yields trillions and trillions of possible portfolios, far too many to evaluate manually. The researchers tested the method on historical market data covering the S&P 100, CSI 300 and Russell 2000, with portfolios of up to 120 assets. For 120 assets, HQCPO produced a score almost 30% higher than classical algorithms in terms of investment return.
At 40 assets, its area under the curve (AUC), a measure of how effectively a model distinguishes stronger from weaker solutions, reached 0.947. An AUC figure approaching 1 would be optimal. Leihua Ai, Quantum computing-driven portfolio optimisation framework for the intelligent economy, International Journal of Information and Communication Technology (2026).
DOI: 10.1504/ijict.2026.156257 MA in English, copy editor since 2021 with experience in higher education and health content. Dedicated to trustworthy science news. Full profile → Master's in physics with research experience.
Long-time science news enthusiast. Plays key role in Science X's editorial success.
Extract — continue reading at the source.
