Quantum kernels show no advantage in stock return prediction, study finds

A new research paper published on arXiv investigates the effectiveness of quantum kernels in predicting stock returns within the Chinese A-share market. The study, which employed rigorous controls to compare quantum fidelity and projected quantum kernels against classical RBF kernels and linear models, found no discernible quantum advantage. Even when using a wider evaluation window and considering full-sample information, quantum kernels did not consistently outperform their classical counterparts or neural baselines. The researchers propose standardized protocols for evaluating quantum advantage claims in finance, emphasizing the need for budget-equalized comparisons and multiplicity-robust inference. AI

RANK_REASON The item is a research paper published on arXiv detailing empirical findings on quantum kernels. [lever_c_demoted from research: ic=1 ai=0.4]

Read on arXiv stat.ML →

• alphaXiv
• CatalyzeX Code Finder for Papers
• Chinese A-share market
• DagsHub
• Gotit.pub
• Hugging Face
• neural baselines
• Nystrom extension
• projected quantum kernel
• quantum fidelity kernel
• quantum kernels
• RBF control
• ScienceCast

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →