Classification of Financial Data Using Quantum Support Vector Machine

ArXiv ID: 2412.10860 “View on arXiv”

Authors: Unknown

Abstract

Quantum Support Vector Machine is a kernel-based approach to classification problems. We study the applicability of quantum kernels to financial data, specifically our self-curated Dhaka Stock Exchange (DSEx) Broad Index dataset. To the best of our knowledge, this is the very first systematic research work on this dataset on the application of quantum kernel. We report empirical quantum advantage in our work, using several quantum kernels and proposing the best one for this dataset while verifying the Phase Space Terrain Ruggedness Index metric. We estimate the resources needed to carry out these investigations on a larger scale for future practitioners.

Keywords: Quantum Support Vector Machine, Quantum Kernels, Time Series Forecasting, Phase Space Terrain Ruggedness Index, Equities

Complexity vs Empirical Score

  • Math Complexity: 7.5/10
  • Empirical Rigor: 4.0/10
  • Quadrant: Lab Rats
  • Why: The paper employs advanced quantum mechanical formalisms, including unitary operators with tensor products of Pauli matrices (e.g., UΦ(x) = exp(…)), which elevates its mathematical density. However, the empirical work relies on small, self-curated datasets (max 460 points) with high sampling noise (max 1024 shots) and lacks backtesting, placing it closer to theoretical exploration than production-ready rigor.
  flowchart TD
    A["Research Goal:<br>Applicability of Quantum Kernels<br>to Financial Data"] --> B["Data Source:<br>Dhaka Stock Exchange Broad Index<br>DSEx"]
    B --> C["Methodology:<br>Quantum Support Vector Machine<br>with Various Quantum Kernels"]
    C --> D["Computation:<br>Train & Evaluate Models<br>on Financial Dataset"]
    D --> E["Key Finding 1:<br>Empirical Quantum Advantage<br>Demonstrated"]
    D --> F["Key Finding 2:<br>Best Kernel Identified<br>via Phase Space Terrain Ruggedness Index"]
    E --> G["Outcome:<br>Resource Estimation<br>for Future Large-Scale Application"]
    F --> G