Employee Performance Aware Intrapreneurial Behavior in Organizational Culture with Analytic Hierarchy Process and Graph based Deep Reinforcement Learning

Abstract

The Analytical Hierarchy Model (AHM) organizes factors influencing Employee Performance in Organizational Culture into a hierarchical framework through two-level comparison on a nine-point scale, creating a standardized assessment matrix with weighted values. To address these difficulties, a novel paradigm called Intrapreneurial Behavior with Analytic Hierarchy and Graph based Deep Reinforcement Learning (IBAHGD)was developed. This system assesses employee performance through intrapreneurial behavior analysis, an analytic hierarchy model, and a graph-based reinforcement learning algorithm to identify proactive, creative employees who enhance organizational performance. The Credamo platform gathered 218 responses from employees and management, resulting in 163 valid replies and a 74.8% response rate, which were statistically, validated using SPSS. The AHM organized the factors influencing Employee Intrapreneurial Behavior Analysis into a hierarchical structure with nine-level pair wise comparisons for evaluation. Ranking uses the eigenvalue method to derive the main eigenvector and maximum eigenvalue, with consistency accessed via the Consistency Index (CI) and Consistency Ratio (CR). The methodology, Graph-based Deep Reinforcement Learning (GDRL), combines deep reinforcement learning and Q-learning for improved decision-making based on total rewards and state-action interactions. The performance analysis is minimum weight based total earliness, IBAHGD C-Metric value analysis, IBAHGD IGD value analysis, IBAHGD S-Metric value analysis.