Performance Analysis of Information Technology Professionals Using Optimal User Clustering and Machine Learning Model for Adaptive e-learning

While considering the digital transformation, the performance analysis of IT professionals is crucial for optimizing adaptive e-learning and skill development programs. However, analyzing user performance requires a robust methodology to handle data inconsistencies, and classify users effectively. For this, user clustering and performance classification is introduced in this research using the optimization algorithm and machine learning model. The user clustering is employed using the proposed Logistic Secretary Bird Optimization (LSeBO) algorithm. Here, the grouping is employed based on their skills, learning behavior, and performance. Then, the Support Vector Machine (SVM)-based performance analysis is employed to classify the clustered users into three performance levels: High Performer (HP), Moderate Performer (MP), and Low Performer (LP).