AI-Driven Feedback System for Remote Work Performance Analysis

Remote and hybrid work models have significantly altered the operational dynamics of organizations, thereby resulting in challenges related to performance management. Traditional evaluation methods have been found to be ineffective as a result of limited supervision and complicated remote situations. This model utilizes machine learning to automatically generate performance reports based on the data. The system employs an ensemble of Logistic Regression, Random Forest, and Gradient Boosting. After being trained on 100,000 employee records consisting of various indicators, the system achieved accuracies of 94.44% (Gradient Boosting), 60.27% (Random Forest), and 29.68% (Logistic Regression) respectively, thus demonstrating the effectiveness of gradient-based methods.The system measures the performance of the employee along seven different dimensions, namely work arrangement, workload, development, engagement, project complexity, work-life balance, and career progression, and accordingly generates personalized recommendations.