predict-students-grades

Here Student Performance Data Set dataset by Data-Science Sean is used to perform EDA and create a machine learning model that can predict student's final grades i.e. Tthe goal is to predict G3 using G1 and G2.

Table of contents

• Getting started
• Findings
• Model performance
• License

Getting started

The notebook is available on Kaggle to work in the same environment where this notebook was created i.e. use the same version packages used, etc...

Findings

age has low positive correlation with failure

Medu & Fedu has moderate positive correlation & they both have low positive correlation with grades

studytime & grades have a low positive correlation

failure has low negative correlation with grades

freetime has low positive correlation with goout

goout has low positive correlation with Walc

Walc has moderate positive correlation with Dalc and they both have negligible negative correlation

Model performance

Learning curve

Loss and R2 square metrics

Actual Vs Predicted values

License

APACHE LICENSE, VERSION 2.0