Student Performance ML Analysis

This project explores the relationships between various student attributes and their academic performance in grades using machine learning techniques. The analysis aims to identify key factors influencing student outcomes and build predictive models for educational insights.

Overview

This repository contains the full workflow of a data-driven analysis of student performance, including:

Data cleaning and preprocessing

Exploratory data analysis (EDA)

Feature engineering

Model training and evaluation

Data conclusions and interpretations

The analysis is used with Python and JupyterLab, with results exported as an HTML report. Additionally, a Google Slides presentation summarizes the key findings and visual highlights of this research.

Objectives

Identify correlations between demographic, social, and academic factors and student grades.

Build predictive models to predict student performance.

Evaluate model accuracy and interpret feature importance for practical takeaways