Quantum Portfolio Optimization with Expert Analysis Evaluation

Abstract

Quantum algorithms have gained increasing attention for addressing complex combinatorial problems in finance, notably portfolio optimization. This study systematically benchmarks two prominent variational quantum approaches, Variational Quantum Eigensolver (VQE) and Quantum Approximate Optimization Algorithm (QAOA), under diverse experimental settings, including different asset universes, ansatz architectures, and circuit depths. Although both methods demonstrate effective cost function minimization, the resulting portfolios often violate essential financial criteria, such as adequate diversification and realistic risk exposure. To bridge the gap between computational optimization and practical viability, we introduce an Expert Analysis Evaluation framework in which financial professionals assess the economic soundness and the market feasibility of quantum-optimized portfolios. Our results highlight a critical disparity between algorithmic performance and financial applicability, emphasizing the necessity of incorporating expert judgment into quantum-assisted decision-making pipelines.

6 pages, 6 figures, 5 tables. Accepted at QCE 2025

References in corpus (5)

• Quantum computing for finance
• Financial Fraud Detection using Quantum Graph Neural Networks
• Financial Fraud Detection: A Comparative Study of Quantum Machine Learning Models
• QFNN-FFD: Quantum Federated Neural Network for Financial Fraud Detection
• QADQN: Quantum Attention Deep Q-Network for Financial Market Prediction

Cited by in corpus (2)

• Evaluating Quantum Amplitude Estimation for Pricing Multi-Asset Basket Options
• IQNN-CS: Interpretable Quantum Neural Network for Credit Scoring