{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T16:40:01Z","timestamp":1792600801857,"version":"4.5.0"},"posted":{"date-parts":[[2026]]},"group-title":"SSRN","reference-count":34,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/www.uspto.gov\/ip-policy\/copyright-policy\/copyright-basics"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:p>Quantum machine learning (QML) is increasingly proposed for financial forecasting and risk analysis, yet comparisons with classical methods almost always stop at accuracy and wall-clock time. As quantum systems approach deployment, their resource footprint \u2014 cryogenic cooling, repeated circuit executions, calibration and the classical optimiser loops surrounding them \u2014 becomes a first-order concern. This paper introduces an energy-aware benchmarking framework for hybrid quantum\u2013classical ML pipelines and applies it to three financial tasks: credit-risk scoring (UCI German Credit) and next-day direction prediction for the S&amp;P 500 and NIFTY 50 indices. Variational quantum classifiers (VQC) and quantum-kernel support vector machines (QSVM) at 4\u20138 qubits are compared with class-weighted logistic regression, RBF-SVM, random forest, XGBoost and a GPU-trained LSTM on identical data subsets. Classical energy is measured directly by a 10 Hz power sampler; quantum energy combines the measured optimisation-loop energy with a per-shot hardware cost model spanning optimistic to pessimistic scenarios. On credit risk the best quantum model (QSVM, 8 qubits) trails logistic regression by 7.8 balanced-accuracy points while consuming 7 \u00d7 1010 times its energy. On index direction all models, classical and quantum, perform at chance, so the 109\u00d7 quantum energy premium purchases nothing. The gap is insensitive to the hardware assumption: break-even would require roughly 10-10 J per shot, ten orders of magnitude below current superconducting systems. Once the statistical uncertainty of the accuracy estimates is taken into account, no quantum model.<\/jats:p>","DOI":"10.2139\/ssrn.7650261","type":"posted-content","created":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T15:46:27Z","timestamp":1792597587000},"source":"Crossref","is-referenced-by-count":0,"title":["Energy-Aware Benchmarking of Quantum Machine Learning for Financial Prediction Tasks: An Accuracy\u2013Sustainability Pareto Analysis of Hybrid Quantum\u2013Classical Pipelines"],"prefix":"10.2139","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4289-114X","authenticated-orcid":true,"given":"Galiveeti","family":"Poornima","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"ref1","doi-asserted-by":"crossref","DOI":"10.1109\/TQE.2020.3030314","article-title":"Quantum computing for finance: state-ofthe-art and future prospects","volume":"1","author":"D J Egger","year":"2020","journal-title":"IEEE Trans. Quantum Eng"},{"key":"ref2","doi-asserted-by":"crossref","DOI":"10.1016\/j.revip.2019.100028","article-title":"Quantum computing for finance: overview and prospects","volume":"4","author":"R Or\u00fas","year":"2019","journal-title":"Rev. Phys"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"450","DOI":"10.1038\/s42254-023-00603-1","article-title":"Quantum computing for finance","volume":"5","author":"D Herman","year":"2023","journal-title":"Nat. Rev. Phys"},{"key":"ref4","first-page":"1","article-title":"Quantum machine learning for finance","author":"M Pistoia","year":"2021","journal-title":"Proc. IEEE\/ACM Int. Conf. Computer-Aided Design (ICCAD)"},{"key":"ref5","doi-asserted-by":"crossref","DOI":"10.22331\/q-2020-07-06-291","article-title":"Option pricing using quantum computers","volume":"4","author":"N Stamatopoulos","year":"2020","journal-title":"Quantum"},{"key":"ref6","volume":"5","author":"S Woerner","year":"2019","journal-title":"Quantum risk analysis, npj Quantum Inf"},{"key":"ref7","doi-asserted-by":"crossref","DOI":"10.1103\/PhysRevResearch.4.013006","article-title":"Dynamic portfolio optimization with real datasets using quantum processors and quantum-inspired tensor networks","volume":"4","author":"S Mugel","year":"2022","journal-title":"Phys. Rev. Res"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"1053","DOI":"10.1109\/JSTSP.2016.2574703","article-title":"Solving the optimal trading trajectory problem using a quantum annealer","volume":"10","author":"G Rosenberg","year":"2016","journal-title":"IEEE J. Sel. Top. Signal Process"},{"key":"ref9","first-page":"3645","article-title":"Energy and policy considerations for deep learning in NLP","author":"E Strubell","year":"2019","journal-title":"Proc. ACL"},{"issue":"12","key":"ref10","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1145\/3381831","volume":"63","author":"R Schwartz","year":"2020","journal-title":"Commun. ACM"},{"key":"ref11","author":"A Lacoste","year":"2019","journal-title":"Quantifying the carbon emissions of machine learning"},{"issue":"248","key":"ref12","first-page":"1","article-title":"Towards the systematic reporting of the energy and carbon footprints of machine learning","volume":"21","author":"P Henderson","year":"2020","journal-title":"J. Mach. Learn. Res"},{"key":"ref13","doi-asserted-by":"crossref","DOI":"10.1103\/PRXQuantum.3.020101","article-title":"Quantum technologies need a quantum energy initiative","volume":"3","author":"A Auff\u00e8ves","year":"2022","journal-title":"PRX Quantum"},{"key":"ref14","doi-asserted-by":"crossref","DOI":"10.1088\/2058-9565\/acae3e","article-title":"Is quantum computing green? An estimate for an energy-efficiency quantum advantage","volume":"8","author":"D Jaschke","year":"2023","journal-title":"Quantum Sci. Technol"},{"key":"ref15","doi-asserted-by":"crossref","DOI":"10.1103\/PRXQuantum.4.040319","article-title":"Optimizing resource efficiencies for scalable full-stack quantum computers","volume":"4","author":"M Fellous-Asiani","year":"2023","journal-title":"PRX Quantum"},{"key":"ref16","doi-asserted-by":"crossref","DOI":"10.1140\/epjqt\/s40507-019-0072-0","article-title":"Engineering cryogenic setups for 100-qubit scale superconducting circuit systems","volume":"6","author":"S Krinner","year":"2019","journal-title":"EPJ Quantum Technol"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"625","DOI":"10.1038\/s42254-021-00348-9","article-title":"Variational quantum algorithms","volume":"3","author":"M Cerezo","year":"2021","journal-title":"Nat. Rev. Phys"},{"key":"ref18","doi-asserted-by":"crossref","DOI":"10.1103\/PhysRevA.101.032308","article-title":"Circuit-centric quantum classifiers","volume":"101","author":"M Schuld","year":"2020","journal-title":"Phys. Rev. A"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1038\/s41586-019-0980-2","article-title":"Supervised learning with quantum-enhanced feature spaces","volume":"567","author":"V Havl\u00ed\u010dek","year":"2019","journal-title":"Nature"},{"key":"ref20","doi-asserted-by":"crossref","DOI":"10.1103\/PhysRevLett.122.040504","article-title":"Quantum machine learning in feature Hilbert spaces","volume":"122","author":"M Schuld","year":"2019","journal-title":"Phys. Rev. Lett"},{"key":"ref21","first-page":"8622","article-title":"Quantum long short-term memory","author":"S Y -C. Chen","year":"2022","journal-title":"Proc. IEEE ICASSP"},{"key":"ref22","author":"A Wack","year":"2021","journal-title":"Quality, speed, and scale: three key attributes to measure the performance of near-term quantum computers"},{"key":"ref23","year":"2026","journal-title":"IBM Quantum, Qiskit Runtime documentation: execution modes and throughput"},{"key":"ref24","doi-asserted-by":"crossref","DOI":"10.1103\/PRXEnergy.4.023008","article-title":"Energy-consumption advantage of quantum computation","volume":"4","author":"F Meier","year":"2025","journal-title":"PRX Energy"},{"key":"ref25","author":"O Knitter","year":"2026","journal-title":"Measuring accuracy and energy-to-solution of quantum fine-tuning of foundational AI models"},{"key":"ref26","doi-asserted-by":"crossref","DOI":"10.1103\/PhysRevA.99.032331","article-title":"Evaluating analytic gradients on quantum hardware","volume":"99","author":"M Schuld","year":"2019","journal-title":"Phys. Rev. A"},{"key":"ref27","volume":"3","author":"L A Barroso","year":"2018","journal-title":"The Datacenter as a Computer: Designing Warehouse-Scale Machines"},{"key":"ref28","author":"H Hofmann","year":"1994","journal-title":"Statlog (German Credit Data), UCI Machine Learning Repository"},{"key":"ref29","author":"I Ragca","year":"2026","journal-title":"S&P500 (^GSPC) -Daily: historical data, Kaggle"},{"key":"ref30","volume":"74017","year":"2015","journal-title":"NSE -Nifty 50 Index Minute data"},{"key":"ref31","author":"V Bergholm","year":"2018","journal-title":"PennyLane: automatic differentiation of hybrid quantum-classical computations"},{"key":"ref32","doi-asserted-by":"crossref","first-page":"1013","DOI":"10.1038\/s41567-021-01287-z","article-title":"A rigorous and robust quantum speed-up in supervised machine learning","volume":"17","author":"Y Liu","year":"2021","journal-title":"Nat. Phys"},{"key":"ref33","article-title":"Power of data in quantum machine learning","volume":"12","author":"H.-Y Huang","year":"2021","journal-title":"Nat. Commun"},{"key":"ref34","doi-asserted-by":"crossref","DOI":"10.1038\/s41598-025-28582-6","article-title":"Carbon efficient quantum AI: an empirical study of ansatz design trade-offs in QNN and QLSTM models","volume":"15","author":"S Tripathi","year":"2025","journal-title":"Sci. Rep"}],"container-title":[],"original-title":[],"deposited":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T15:50:42Z","timestamp":1792597842000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ssrn.com\/abstract=7650261"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":34,"URL":"https:\/\/doi.org\/10.2139\/ssrn.7650261","relation":{},"subject":[],"published":{"date-parts":[[2026]]},"subtype":"preprint"}}