Analysis of Cost Control and Quality Improvement Paths for Geriatric Elderly Care Services under Long-term Care Insurance

Efficient management of large-scale service systems requires robust information integration, intelligent resource allocation, and data-driven decision support. This study proposes a cost-control and quality-optimization framework based on multimodal data fusion, efficiency evaluation, and simulation-driven decision analysis. Heterogeneous information from administrative records, clinical indicators, caregiver surveys, and policy datasets is integrated through a unified data-processing architecture to support comprehensive system assessment. Principal component analysis, regression modeling, and Super-SBM efficiency evaluation are employed to identify key determinants affecting service utilization, resource allocation, and outcome performance. To further enhance system adaptability, Monte Carlo simulation and agent-based modeling are incorporated to characterize uncertainty propagation, dynamic interactions, and long-term optimization effects. Experimental results demonstrate that the proposed framework improves service efficiency by up to 18%, reduces out-of-pocket expenditure by 15%, decreases caregiving burden by 20%, and enhances overall quality-of-life indicators by 14% under simulated conditions. The proposed framework provides an effective methodology for heterogeneous information fusion, intelligent decision support, system-level optimization, and dynamic resource management, offering potential applications in distributed monitoring, data-driven service systems, and complex networked environments.