Landscape-Dependent Performance of Photonic Quantum Solvers in QUBO Feature Selection for Financial Risk Detection
Abstract
Feature selection for imbalanced classification tasks such as credit card fraud and consumer default detection requires balancing predictive relevance, inter-feature redundancy, and computational feasibility. We benchmark three computing paradigms, classical branch-and-bound optimization (Gurobi), photonic entropy computing (QCI Dirac-3), and simulated photonic boson sampling (Piquasso), across thirteen feature-selection methods on two datasets: ULB Credit Card Fraud (30 features) and AmEx consumer default (159 features). Each method is routed to the solver matched to its mathematical structure. On ULB, Dirac-3 MI-Spearman matches the all-features model using 13 of 30 features (mean F1 0.873 +/- 0.023 over five runs, best run 0.896), and Piquasso is the best method at k=5. On AmEx, performance rises steadily with the feature budget and every paradigm approaches F1 = 0.80 only near the full feature set. Most differences between Gurobi and Dirac-3 on identical methods fall within run-to-run variation; the large gaps occur where the certified optimum generalizes poorly, most sharply for distance correlation on AmEx at k=25 (Gurobi F1 = 0.422 vs. a Dirac-3 mean of 0.746). At matched budgets, F1 varies about ten times more across methods on ULB than on AmEx, which we trace to how concentrated the predictive signal is in each feature space.
Related
- Depth-Efficient Quantum Topological Data Analysis for Regime-Specific Detection of Financial Stress
- Exploring the SMEFT landscape: Bayesian Model Selection for indirect discovery
- Exploring the SMEFT landscape: Bayesian model selection for indirect discovery
- A Centre-Charge Selection Rule for the Wilson-Line Potential: The Fundamental Domain of Gauge-Higgs Unification Is Representation-Dependent (Part III)
- ProtocolMatch: Protocol-Dependent Model Selection for Scientific Dynamics Forecasting
BibTeX
@misc{sahoo2026landscapedependent,
title = {{Landscape-Dependent Performance of Photonic Quantum Solvers in QUBO Feature Selection for Financial Risk Detection}},
author = {Nirvik Sahoo and Paul Robert Griffin},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.03161},
eprint = {2610.03161},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.03161},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Landscape-Dependent Performance of Photonic Quantum Solvers in QUBO Feature Selection for Financial Risk Detection
AU - Nirvik Sahoo
AU - Paul Robert Griffin
PY - 2026
DA - 2026/10/02
PB - arXiv
DO - 10.48550/arxiv.2610.03161
UR - https://arxiv.org/abs/2610.03161
AB - Feature selection for imbalanced classification tasks such as credit card fraud and consumer default detection requires balancing predictive relevance, inter-feature redundancy, and computational feasibility. We benchmark three computing paradigms, classical branch-and-bound optimization (Gurobi), photonic entropy computing (QCI Dirac-3), and simulated photonic boson sampling (Piquasso), across thirteen feature-selection methods on two datasets: ULB Credit Card Fraud (30 features) and AmEx consumer default (159 features). Each method is routed to the solver matched to its mathematical structure. On ULB, Dirac-3 MI-Spearman matches the all-features model using 13 of 30 features (mean F1 0.873 +/- 0.023 over five runs, best run 0.896), and Piquasso is the best method at k=5. On AmEx, performance rises steadily with the feature budget and every paradigm approaches F1 = 0.80 only near the full feature set. Most differences between Gurobi and Dirac-3 on identical methods fall within run-to-run variation; the large gaps occur where the certified optimum generalizes poorly, most sharply for distance correlation on AmEx at k=25 (Gurobi F1 = 0.422 vs. a Dirac-3 mean of 0.746). At matched budgets, F1 varies about ten times more across methods on ULB than on AmEx, which we trace to how concentrated the predictive signal is in each feature space.
ER -