ABSTRACT
The utilization of predictive algorithms in human resources using machine learning techniques provides an important part in obtaining automatic data-driven decisions. The performance of predictive models in the field of human resources is implemented through machine learning evolving genetic algorithms. This helps to optimize various HR tasks such as performance evaluation, task management, and recruitment process and talent management system. The genetic algorithm is used for fine-tuning the hyperparameters which helps in enhancing the accuracy and reliability of the system. They also help to obtain the interpretability of the predictive models. The genetic algorithm is utilized in the identification of the most relevant features and hyperparameters for each model in the recruitment process resulting in improved predictive performance. The real-world HR datasets help in evaluating the effectiveness of the proposed approach. Various performance metrics such as accuracy, recall, precision and F1 score are necessary for the analysis of the proposed model with ML algorithms. The interpretability of the optimized model is evaluated to determine that the results are actionable in HR decision-making processes. Thus, the proposed system provides a valuable approach for HR practitioners to extract the full potential of the genetic algorithm in human resource management. This aims to achieve and contribute to the advancement of predictive analytics in human resources by validating the effectiveness of machine learning with optimization algorithms.
