Student Performance Patterns Analysis for Decision Making

Printer-friendly version

Ever since computers were invented, we have wondered whether they might be made to learn. A successful understanding of how to make computers learn would open many new uses of computers and new levels of competence and customization. And a detailed understanding of information processing algorithms for machine learning might lead to a better understanding of human learning abilities (and disabilities) as well.

     We do not yet know how to make computers learn nearly as well as people. However, algoritms have been invented that are effective in certain types of learning tasks, and a theoretical understanding of learning is benning to emerge.

     It is with this inspiration that the researcher wishes to use some of these Machine Learning algorithms to Learn Student Performance Patterns and Association as well as Prediction in a typical College: Kenya School of Monetary Studies.

     Implementing a technique that is efficient yet accurate for college student performance is of significant importance.

     In this project I’ll examine student performance predictions and associations.

     Using Decision Trees, the mean grade, English, Mathematics, Continuous performance, attendance and Mock Examination were found to be the best preditors of success (Performance in Final-External Examination).

     Using these features, peformance based on decision trees was contrasted with Neural Network and KNN as an alternative to prediction.

UoN Website | UoN Repository | ICTC Website

Copyright © 2018. ICT WebTeam, University of Nairobi