Big Data-Driven Optimization Model for Art Education Resource Allocation in China

The authors developed a big data-driven optimization model for art education resource allocation by integrating cloud computing, data mining, and machine learning to address regional and institutional imbalances and overcome the limitations of traditional empirical allocation methods. To achieve this, they analyzed the current resource allocation practices; built a platform to collect data on student performance, teacher effectiveness, and facility usage; and applied clustering, association rule mining, and regression techniques in three case studies. The results indicated that the big data-driven approach reduced the disparity in teacher-student ratios by 44.8%, increased digital equipment coverage in under-resourced areas by 261.1%, narrowed inter-school disparities by over 50%, and achieved a 92.4% growth in online resource engagement, along with an 88.3% reduction in policy response time. These findings suggest that big data analysis can facilitate accurate demand diagnosis, dynamic optimization, and more equitable distribution of art education resources, offering a replicable framework for data-driven educational decision-making.