A Comparative Analysis of Machine Learning Algorithms to Predict Academic Performance using KDD methodology

Repository of Individual Project (SID:10002997)

This repository contains the dataset, files and code used for my Computer Science with Artificial Intelligence dissertation. The aim of this project was to answer the following questions:

• How accurately can different machine learning algorithms predict academic performance in higher education?

• To what extend does different student features influence academic performance predictions?

Authors

• Philbert Baby- Project Manager
• Aram Saeed - Supervisor

Installation

To run the .ipynb code file, please download the following software:

• Jupyter Notebook

To set up the working environment on Jupyter notebook, please download the following libraries :

!pip install pandas numpy matplotlib seaborn plotly 
!pip install tensorflow keras livelossplot scikit-learn Pillow
!pip install openpyxl
!pip install xgboost

Acknowledgements

• Coventry University - Dissertation submitted on behalf of this Univeristy.
• Universidad Tecnologica de Bolivar - Obtained the Dataset from this University.
• Enrique De La Hoz - Developed the dataset used in this research.

License

• This project is licensed under the MIT License - see the MIT file for further details.

• The dataset used in this research is licensed by the CC BY 4.0 licence - see the CC 4.0 for further details.