Predicting Management Skills of Undergraduate Students by Leveraging Different Machine Learning Classifiers

In today's dynamic and competitive environment, the need for effective management skills among engineering undergraduate students is pivotal for their success in various professional domains. These skills lay the groundwork for future leadership roles in various professional settings. Whether in business, healthcare, education, or technology, the ability to manage oneself, teams, projects, and resources efficiently is fundamental for career advancement. Moreover, possessing strong management skills fosters effective decision-making, problem-solving, and communication abilities, which are highly sought-after qualities in today's competitive job market. The objective is to leverage machine learning techniques to analyze data sets encompassing six underlying dimensions of management skills namely management planning and control, risk management, configuration management, decision management, project management, quality management, and information management to build predictive models. These models aim to assess and forecast the potential management capabilities of undergraduate students. This study will utilize four popular machine learning algorithms: Logistic Regression, Support Vector Machine, К-Nearest Neighbors, Naïve Bayes, and Random Forest to develop a model based on a set of predictors, tune and cross-validate them, and select the best model that can accurately predict the effective management skills of engineering undergraduate students. The proposed models will provide trustworthy and precise forecasts and will empower engineering students to navigate complexities, adapt to changes, and lead initiatives, contributing to their personal and professional growth.