This research addresses the analysis of the level of stress faced by university students of industrial engineering located in metropolitan Lima through data mining tools. In normal situations, the daily load of the student from the eighth to the tenth cycle of a university was divided between university studies and the work of professional practices required in the curriculum, which meant an average load of 25 hours of classes, 30 hours of work in a company and 33 hours of study in the execution of academic tasks per week. This load has been affected since March 15, 2020, when the Ministry of Education established distance education - virtual and the Ministry of Health established confinement due to COVID 19, which impacted on a higher level of stress. The first phase of the research began with data collection, for this phase the SISCO Academic Stress Inventory proposed by Rosanna [1] was used; in the second phase the data preprocessing was carried out; In the third phase, it was identified which are the significant variables that influence a high level of stress measurement of the students, the main methods being the use of logistic regression and the classification tree; In the third phase, the level of precision of the proposed methods were validated, in the logistic regression method a model with a p_value of 95.7%, and a value of the Akaike criterion; In the classification tree method, a precision level of 78% was obtained; Finally, it was determined which are the significant variables that affect the level of stress of the students, such as the ergonomic conditions for studying and carrying out activities at home, which are on average 20 hours a week. The research concludes with the measurement and characterization of the level of stress, recommendations to teachers to be able to motivate students, and look for complementary tools to strengthen learning.