The satisfaction of employees is of utmost importance for the development and sustainability of companies. A satisfied and happy employee in their current position is less likely to consider leaving their job, leading to a stronger commitment to their work and a greater contribution to the company. The aim of this study is to analyze employee engagement, satisfaction, and sensitivity, using machine learning methods to facilitate insights into workforce dynamics and guide improvement strategies. The dataset used includes personal and in-company demographic information for 3,000 employees, as well as information on their personal development through training. Machine learning algorithms (gradient boosting, k-nearest neighbors, logistic regression, random forest, support vector machines) were applied for classification related to employee performance. Parameter optimization was carried out for the algorithms in the application. Additionally, the factors influencing employee performance and their levels of importance were determined.