From IceCube to IT-Sphere: A Hybrid Quantum-Classical GNN for Banking IT Root Cause Analysis
Abstract
We present Hybrid Quantum Root Cause Analysis (HQ-RCA), an industrially grounded workflow for root cause analysis in banking IT operations, built on a hybrid Quantum Graph Neural Network (QGNN): the classical backbone of DynEdge (the IceCube neutrino-reconstruction GNN, which we call standalone DynEdge), with its classification head replaced by a Variational Quantum Circuit (VQC). On 13 months of anonymised IT data (13k alarm clusters) from a major European bank, the hybrid QGNN matches standalone DynEdge -- the strongest classical baseline -- on F1, while standalone DynEdge leads the ranking metrics. A readout-sensitivity and layout-robustness study, analysed via Dimensional Expressivity Analysis (DEA), shows that the effective parameter dimensionality (rank) of the quantum observable has no measurable correlation with F1; we therefore keep the simplest readout ⟨ Z0⟩ (the Pauli-Z expectation on the first qubit), which in the deployed layout is rank-1, collapsing optimisation to a 1-D problem solvable by a gradient-free grid scan. Execution on IBM Heron r2 (no error mitigation) shows this gradient-free readout is executable on NISQ hardware after threshold recalibration.
Related
- Exact diffusion coefficients for quantum--classical hybrid walks
- Learning nuclear mass systematics with hybrid quantum-classical mixtures of experts
- Hybrid Variational Quantum-Classical Framework with Adaptive Weighting and Efficiency Assessment
- HTM: A Hybrid Classical-Quantum Computation Model
- Quantum-Classical Hybrid Methods for Optimization: Lessons from Classical Decomposition
BibTeX
@misc{greco2026from,
title = {{From IceCube to IT-Sphere: A Hybrid Quantum-Classical GNN for Banking IT Root Cause Analysis}},
author = {Antonio Greco and Riccardo Paoletti and Roberto Cappuccio and Mario Onorato},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.22822},
eprint = {2609.22822},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.22822},
}
RIS
TY - UNPB
TI - From IceCube to IT-Sphere: A Hybrid Quantum-Classical GNN for Banking IT Root Cause Analysis
AU - Antonio Greco
AU - Riccardo Paoletti
AU - Roberto Cappuccio
AU - Mario Onorato
PY - 2026
DA - 2026/09/19
PB - arXiv
DO - 10.48550/arxiv.2609.22822
UR - https://arxiv.org/abs/2609.22822
AB - We present Hybrid Quantum Root Cause Analysis (HQ-RCA), an industrially grounded workflow for root cause analysis in banking IT operations, built on a hybrid Quantum Graph Neural Network (QGNN): the classical backbone of DynEdge (the IceCube neutrino-reconstruction GNN, which we call standalone DynEdge), with its classification head replaced by a Variational Quantum Circuit (VQC). On 13 months of anonymised IT data (13k alarm clusters) from a major European bank, the hybrid QGNN matches standalone DynEdge -- the strongest classical baseline -- on F_1, while standalone DynEdge leads the ranking metrics. A readout-sensitivity and layout-robustness study, analysed via Dimensional Expressivity Analysis (DEA), shows that the effective parameter dimensionality (rank) of the quantum observable has no measurable correlation with F_1; we therefore keep the simplest readout ⟨ Z_0⟩ (the Pauli-Z expectation on the first qubit), which in the deployed layout is rank-1, collapsing optimisation to a 1-D problem solvable by a gradient-free grid scan. Execution on IBM Heron r2 (no error mitigation) shows this gradient-free readout is executable on NISQ hardware after threshold recalibration.
ER -