Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{200234,
        author = {Khushi Verma and Palanivel R},
        title = {A Hybrid Quantum-Classical Approach for Event Classification Using CERN Open Data},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {12},
        pages = {4155-4161},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=200234},
        abstract = {This paper presents a hybrid quantum-classical framework for classifying CERN CMS Open Data events containing charged leptons and neutrinos. A balanced dataset of 200,000 events was formed by combining 100,000 Wmunu and 100,000 Wenu samples, from which 26 engineered kine- matic and detector-level features were constructed. Classical baselines based on XGBoost, LightGBM, and CatBoost achieved 100.0% accuracy, 100.0% precision, 100.0% recall, 100.0% F1-score, and 1.000 ROC-AUC on the held-out test set. The quantum branch used median imputation, standard- ization, PCA reduction to four components, angle encoding on a 4-qubit circuit, and a PennyLane quantum kernel with an SVM classifier. The best quantum configuration achieved 99.0% accuracy, 98.04% precision, 100.0% recall, 99.01% F1-score, and 1.000 ROC-AUC on a balanced 100-event subset, with 49 true negatives, 1 false positive, 0 false negatives, and 50 true positives. The results confirm that compact quantum-kernel learning is competitive, although classical ensembles remain superior on this highly separable benchmark.},
        keywords = {Quantum Machine Learning, CERN Open Data, Quantum Kernel, Event Classification, Support Vector Machine, Hybrid Learning},
        month = {May},
        }