Paper: arXiv 2611.10801

Authors: Chi-Sheng Chen, Xinyu Zhang, En-Jui Kuo, Rong Fu, Qiuzhe Xie, Fan Zhang

Abstract

Hybrid quantumclassical models are increasingly proposed for nancial prediction, but reported gains are rarely separated from the classical components around them. We study a hybrid quantum temporal convolutional network for daily cross-sectional ranking of 2000 Tokyo Stock Exchange equities under a protocol built to make the quantum contribution identiable: six conditions (circuit trained, frozen or absent, a parameter-matched classical surrogate, and the circuit alone, trained or frozen) through one code path; four walk-forward folds with ve seeds; bootstrap intervals, Deated Sharpe Ratios, backtest-overtting probabilities and family-wise error control; ve classical baselines including a gradient-boosted tree; and a locked holdout. On 500 out-of-sample days two one-sided tests place the trained-versus-frozen dierence inside 0.03 annualised Sharpe (p = 0.0055, minimum detectable eect 0.02): the circuit is equivalent to a frozen one, not merely indistinguishable from it. With the circuit as the head’s only input the two are equivalent inside 0.25; against the network with no circuit the design resolves only 0.50. No condition is distinguishable from zero (best De-ated Sharpe Ratio 0.17). The holdout reproduces the ablation on a protable window, and 2000 US equities reproduce it where every condition loses money.

Complexity vs Empirical Score

  • Math Complexity: 6.5/10
  • Empirical Rigor: 9.5/10
  • Quadrant: Holy Grail — high math complexity, high empirical rigor

Why this score: This paper demonstrates exceptional empirical rigor through its robust backtesting protocol, statistical controls, and self-auditing approach. While the core quantum models might not be entirely novel, the rigorous methodology for isolating and evaluating their contribution, especially in a null-result context, is highly novel and valuable. The paper is also remarkably clear and committed to reproducibility.

Research Flowchart

  flowchart TD
    A[Research Goal: Identify Quantum Layer Contribution to Equity Ranking] --> B{Methodology: Hybrid Quantum-Classical Model Analysis};
    B --> C[Data/Inputs: Daily Cross-Sectional Ranking of 2000 TSE Equities];
    C --> D{Computational Processes:};
    D --> D1[-- 6 Conditions (Trained/Frozen/Absent Circuit, Classical Surrogate, Circuit Alone)];
    D1 --> D2[-- 4 Walk-Forward Folds, 5 Seeds];
    D2 --> D3[-- Bootstrap Intervals, Deflated Sharpe Ratios, Backtest-Overfitting, FWE Control];
    D3 --> D4[-- 5 Classical Baselines, Locked Holdout];
    D4 --> E[Key Findings: Quantum Circuit Contribution is Minimal];
    E --> F[Outcomes: Trained vs. Frozen Circuit Difference < 0.03 Annualized Sharpe (p=0.0055)];
    F --> G[Outcomes: Circuit Equivalent to Frozen, Not Merely Indistinguishable];
    G --> H[Outcomes: No Condition Distinguishable from Zero (Best Deflated Sharpe Ratio 0.17)];