Skip to content

This project aims to predict student performance when there is less number of student records present. It basically addresses the problem of low to medium-sized schools and universities which want to create a performance prediction system for their students.

License

Notifications You must be signed in to change notification settings

Sarthak-10/Student-Performance-Prediction-and-Analysis-for-low-resource-scenario

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Student-Performance-Prediction-and-Analysis-for-low-resource-scenario

Open In Colab

Please star the repository if you happen to like the project

It is important to develop Student Performance prediction software. It helps educational entities and institutes in understanding the shortcomings of the current educational process and suggests improvements in our current system. It can also be used to take early precautions in order to improve students’ performance in academic endeavors. Another application of such a system can be to select the right student for a particular task.

We also need to figure out the reasons that lead to poor performance of the students. Factors like extracurricular activities, illnesses, financial problems, and family problems have a major effect on students' performance.

We used a dataset, which was collected from two Portuguese schools in the subject of Portuguese. Here we have developed 8 models. We used both the techniques in permutations of: -

  1. using dataset with grades and without grades
  2. regression (0-20) and 4-level classification Furthermore, we also reviewed two research papers which predict student performance so as to understand techniques used by researchers in similar settings.

The detailed results and analysis can be found in the report as well as the slides attached.

About

This project aims to predict student performance when there is less number of student records present. It basically addresses the problem of low to medium-sized schools and universities which want to create a performance prediction system for their students.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published