OQC, Citi, and NQCC Evaluate Quantum-Compressed PINNs for Financial Derivative Pricing Workflows
Oxford Quantum Circuits, Citi, and the UK's National Quantum Computing Centre completed a joint study on Quantum-compressed Physics-Informed Neural Networks (QPINNs) for pricing financial derivatives. The evaluation found that QPINNs could reduce model complexity while preserving pricing accuracy. The work targeted workflows relevant to Citi's derivatives business.
AI analysis — not reported by the source
What this could mean
- 0–2 yearsPlausible
Within two years, Citi could begin piloting QPINN-based pricing models on OQC's superconducting hardware for internal risk analytics on complex derivatives, if the compression technique scales beyond the study's test cases.
The study already demonstrates accuracy-preserving model compression, which addresses a key obstacle to running neural pricing models on near-term quantum devices. The remaining steps are validating on larger, more heterogeneous derivative portfolios and integrating with existing risk infrastructure, which are engineering challenges rather than fundamental physics.
This is a brief. The day’s lead story carries the full analysis.