End-to-End Portfolio Optimization with Quantum Annealing

ArXiv ID: 2504.08843 “View on arXiv”

Authors: Unknown

Abstract

Hybrid-quantum classical optimization has emerged as a promising direction for addressing financial decision problems under current quantum hardware constraints. In this work we present a practical end-to-end portfolio optimization pipeline that combines (i) a continuous mean-variance and Sharpe-ratio formulation, (ii) a QUBO/CQM-based discrete asset selection stage solved using D-Wave’s hybrid quantum annealing solver, (iii) classical convex optimization for computing optimal asset weights, and (iv) a quarterly rebalancing mechanism. Rather than claiming quantum advantage, our goal is to evaluate the feasibility and integration of these components within a deployable financial workflow. We empirically compare our hybrid pipeline against a fund manager in real time and indexes used in Indian stock market. The results indicate that the proposed framework can construct diversified portfolios and achieve competitive returns. We also report computational considerations and scalability observations drawn from the hybrid solver behaviour. While the experiments are limited to moderate sized portfolios dictated by current annealing hardware and QUBO embedding constraints, the study illustrates how quantum assisted selection and classical allocation can be combined coherently in a real-world setting. This work emphasizes methodological reproducibility and practical applicability, and aims to serve as a step toward larger-scale financial optimization workflows as quantum annealers continue to mature.

Keywords: Portfolio Optimization, Quantum Annealing, QUBO, Hybrid Quantum-Classical, Mean-Variance

Complexity vs Empirical Score

• Math Complexity: 5.5/10
• Empirical Rigor: 6.5/10
• Quadrant: Holy Grail
• Why: The paper introduces advanced mathematical formulations like QUBO/CQM for discrete asset selection and integrates them with classical convex optimization, but relies on a hybrid quantum annealing solver that is not fully code-reproducible. It demonstrates real-time empirical comparisons against a fund manager and Indian market indexes, yet the experiments are limited by current hardware constraints, indicating practical feasibility but not full backtest readiness.

  flowchart TD
    A["Research Goal: Feasibility of<br/>End-to-End Hybrid Quantum<br/>Portfolio Optimization"] --> B["Data Input:<br/>Indian Market Data<br/>(Nifty 50 constituents)"]
    B --> C["Hybrid Quantum-Classical Pipeline"]
    
    subgraph C [" "]
        direction TB
        C1["Stage 1: Discrete Selection<br/>QUBO/CQM Formulation<br/>D-Wave Hybrid Solver"]
        C2["Stage 2: Continuous Allocation<br/>Classical Convex Optimization<br/>Mean-Variance & Sharpe Ratio"]
    end
    
    C --> D["Operational Process:<br/>Quarterly Rebalancing"]
    D --> E["Key Outcomes & Findings"]
    
    subgraph E [" "]
        direction TB
        E1["✓ Competitive Returns<br/>vs. Fund Manager & Indices"]
        E2["✓ Diversified Portfolios<br/>Constructed"]
        E3["✓ Practical Feasibility<br/>Demonstrated"]
        E4["Current Constraints:<br/>Moderate Portfolio Size<br/>(Hardware/QUBO embedding limits)"]
    end