Data Quality Assessment Based on Single‐Valued Neutrosophic Credibility Numbers: A Multi‐Attribute Group Decision‐Making Approach Integrating Cumulative Prospect Theory and Bidirectional Projection Measure

ABSTRACT Data quality assessment is a critical process for enabling efficient data utilisation and supporting scientifically sound decision‐making. It not only provides a reliable foundation for data analysis, machine learning, and intelligent decision‐making but also serves as a core enabler for the market‐based allocation of data resources and the practical realisation of data value. However, existing assessment frameworks often fail to comprehensively capture the fuzziness, uncertainty, and credibility inherent in real‐world information. To address these challenges, this study develops a novel multi‐attribute group decision‐making (MAGDM) framework based on single‐valued neutrosophic credibility numbers (SvNCNs). First, a new scoring function is proposed to overcome the mathematical limitations of existing SvNCN models. This function systematically integrates true, false, and indeterminate fuzzy information along with their associated credibility, effectively reducing distortions caused by uncertainty and enhancing the interpretability and robustness of the results. Second, a weighting method combining SvNCN‐PIvot Pairwise RElative Criteria Importance Assessment (PIPRECIA) and Grey Relational Analysis (GRA)‐Criteria Importance through Intercriteria Correlation (CRITIC) is employed to achieve an organic integration of subjective and objective weights, ensuring the scientific rigour of the weight determination process. Third, a bidirectional projection measure is introduced in the SvNCN environment to comprehensively evaluate the relationship between alternatives and the positive and negative ideal solutions, thereby improving ranking accuracy; meanwhile, cumulative prospect theory (CPT) is incorporated to capture decision‐makers' psychological preferences and behavioural characteristics under uncertainty, enhancing the framework's practical applicability and decision rationality. Case validation based on data quality assessment demonstrates that the proposed framework outperforms existing approaches in terms of ranking accuracy, robustness, and decision rationality.