Cost Optimization in Sports Organizations Through Human-Centric Service Using an Artificial Neural Network

Abstract

Human resource management mode describes the established style of management used by sports organizations to oversee the conduct of their own Sports employees throughout their businesses' long-term operations. Sports institutions need optimization and improvement in human resource development and management as society evolves to maintain or increase its market share and social competitiveness. Institutional success often hinges on how well they foster and direct their people resources. Human resource economic management is an improved human resource development and management model that has evolved alongside other sports institutions and the advancement of knowledge under human-centric service. In this context, learning how best to maximize the cost-effectiveness of institutional human resource management is a topic of significant importance in human-centric service. First, this work proposes a series of optimization measures for the economic management mode of human resources in sports institutions from different aspects. Second, this work proposes an IFWA-ELM algorithm for evaluating human resource economic management models in sports institutions. Specifically, this work uses the Cauchy mutation operator to replace the Gaussian mutation operator, uses the elite random selection strategy to replace the original selection strategy, introduces the difference mutation operator and the reverse learning operator to propose IFWA. Then use IFWA to optimize the ELM's input weights and hidden layer thresholds to establish the IFWA-ELM algorithm. Third, this work conducts systematic experiments to verify the superiority of the optimization measures and the IFWA-ELM algorithm.