Trust-Aware Data Pipelines: Ensuring Reliability and Governance in Large-Scale ML Systems
Abstract
We present a production-grade hybrid quantum�classical architecture that accelerates feature selection and bandit policy tuning for large-scale recommender systems. Evaluated on 1.2B events, the approach reduced training time by 28% and improved CTR by 3.7% compared to strong baselines.
Cite this article
Pulicharla, M. R., Menon, P., & Zhang, W. (2025). Trust-Aware Data Pipelines: Ensuring Reliability and Governance in Large-Scale ML Systems. Research Explorations in Global Knowledge & Technology (REGKT), 3 (1). Retrieved from https://regkt.com/article.php?id=101&slug=hybrid-quantum-classical-pipelines-for-real-time-recommendations