Transition from traditional social indicators to a social credit score in assessing society

Purpose Traditional social indices often fail to fully assess the state of society in the context of modern digital transformation. This poses challenges for governance and decision-making in the context of a digital state. To address this issue, we propose an Artificial Intelligence (AI) – based weighting system that combines different international indices and optimization methods into a single model to enhance the precision of societal assessment. Design/methodology/approach We propose the SCS-SWBI Model based on a two-tier calculation framework: first, an individual Social Credit Score (SCS) is determined, followed by a collective Social Well-Being Index (SWBI). The model's structural weights (α, β, ω, and γ) are optimized using a hybrid application of Gradient Descent and Reinforcement Learning. Findings A simulated synthetic population of 1,000 profiles was used in the analysis. The study's result (social system equilibrium point: Vmean = 0.755) demonstrates that the SCS-SWBI Model can provide a rapid assessment of socioeconomic processes, monitoring of societal well-being, and policy impact in real time. Research limitations/implications Although the study uses reliable synthetic variables, the findings need to be further validated using large-scale, real-world empirical data. Practical implications The SCS-SWBI Model provides government agencies with a strategic tool for conducting real-time assessments of socio-economic processes. Originality/value The originality lies in the hybrid application of Gradient Descent and Reinforcement Learning to dynamically adjust societal weights, providing a more accurate reflection of the non-linear relationship between individual behavior and macro-level social progress than traditional statistical models.