Digital twins are increasingly adopted to support data-driven decision-making in complex and dynamic systems . However, existing digital twin–based approaches for risk analysis and prediction often rely on isolated predictive models and lack native support for multidimensional analytics , thus limiting their ability to provide comprehensive and interpretable insights. In order to fulfill this gap, the paper proposes a novel multidimensional big data analytics framework for risk analysis and prediction over digital twins . The framework integrates streaming data ingestion, distributed multidimensional modeling, analytics, and predictive modeling within a unified cloud-native architecture. Risk prediction is embedded within the multidimensional analytics pipeline, enabling context-aware and interpretable predictions across multiple analytical perspectives. The proposed approach is evaluated using real-world datasets through a combination of multidimensional exploratory analysis and quantitative baseline comparisons with standard Machine Learning (ML) models. Experimental results demonstrate that the framework achieves competitive predictive performance while supporting scalable, interpretable, and multidimensional risk analysis. These characteristics make the proposed solution particularly suitable for complex digital twin scenarios where both analytical flexibility and predictive reliability are required.

Focusing on the innovative context that predicates the integration between digital twin technologies and big data paradigms, including management and analytics, this paper proposes models, principles and implementations of a framework for supporting multidimensional risk analysis and prediction over digital twins. We complement our research contributions by means of a comprehensive experimental campaign over real-life datasets that focus on the emerging digital twin healthcare setting.