INES – National Institute of Science and Technology for Software Engineering

RSS feed


Calendar

November 2021
M T W T F S S
« Nov    
1234567
891011121314
15161718192021
22232425262728
2930  

 
  • INES at KDMILE 2015

    (0)
    Publicado em September 15th, 2015Uncategorized

    The MsC student Allan Sales will attend the 3rd Symposium on Knowledge Discovery (KDMILE 2015), where the paper:  “Predicting Student Dropout: A Case Study in Brazilian Higher Education” will be presented.

    Abstract

    Students’ dropout is a major concern of Brazilian higher education institutions because it can result in waste of resources and hence decrease the graduation rates. Most of the dropouts occur in the initial semesters of a course, especially in the first one, where students are still uncertain about the career they want to follow. Thus, the early detection of students with high probability of dropping out, as well as understanding the underlying causes, are crucial for defining more effective actions towards preventing this problem. In this paper, we cast the dropout detection problem as a classification problem. We use a large sample of academic records of students across 130 courses from a public University in Brazil in order to select informative features for the employed classifiers. Considering only first semester students as targets, we conduct a thorough evaluation of several state-of-the-art classification models and show that good results can be achieved considering only a small, but informative, number of features.

Leave a Reply

You must be logged in to post a comment.