Work

MERLIN SCIENCE — Loan Portfolio Optimization with Variational Quantum Algorithms — E8 Intelligence Research

Year: 2026
Type: preprint
Abstract: Today, I'm excited to share a groundbreaking advancement in the field of finance and quantum computing: we have developed a framework for loan portfolio optimization using variational quantum algorithms. Loan portfolio optimization, or LPO, is critical in financial services as it seeks to construct portfolios that minimise credit risk while adhering to practical constraints in selection. This process involves complex modelling of both expected losses and the variability of those losses, as well as the correlations between borrower defaults. As portfolio size increases, the complexity of the optimisation problem grows rapidly, requiring innovative solutions. Our approach formulates LPO as a Quadratic Constrained Binary Optimization problem. This enables us to jointly capture the expected and unexpected losses inherent in lending. We then transform this formulation into a Quadratic Unconstrained Binary Optimization model, which is well-suited for variational quantum optimisation techn Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com
Language: English
Open Access status: green
OpenAlex ID: W7236356184
Cites:
Cited by:
Related to: 10