Advanced Quantum Machine Learning project comparing Hybrid VQC and Quantum Kernel SVM, featuring modular pipeline, and automatic artifact logging

Author: Ahmad Rasidi¹¹ Independent Researcher; Undergraduate Student (3rd Semester, Bachelor’s Program), Bumigora University, Indonesian Abstract:Quantum Machine Learning (QML) stands at the frontier of near-term quantum computing applications, promising enhanced pattern recognition through quantum mechanical principles. However, empirical validation of QML models under Noisy Intermediate-Scale Quantum (NISQ) constraints remains fragmented and often lacks reproducibility and cross-platform consistency. This work presents a comprehensive benchmark comparing two canonical QML paradigms Hybrid Variational Quantum Classifier (VQC) and Quantum Kernel Support Vector Machine (QSVM) using a unified open-source framework built on PennyLane, PyTorch, Qiskit, and scikit-learn. The study introduces a reproducible, modular, and cross-device pipeline featuring YAML-driven configuration, deterministic seeding, automatic artifact logging, and support for CPU, CUDA, and MPS execution. Across five independent experimental runs (seeds 1001–1005), we evaluate test accuracy, F1-score, and ROC-AUC. Results show that the Hybrid VQC achieves a mean accuracy of 79.8% ± 6.3%, while QSVM exhibits instability with a mean accuracy of 50.3% ± 0.0% and F1-score variance ±0.299, highlighting the fragility of quantum kernel methods under small-scale conditions. The accompanying repository (GitHub – rasidi3112/Quantum-Machine-Learning) enables full reproducibility of all results and artifacts. This work establishes a transparent, statistically grounded benchmark for QML under NISQ constraints. “This document was partially refined using ChatGPT (OpenAI), and all content has been reviewed by the author.”