An in-depth Exploratory Data Analysis (EDA) project designed to uncover patterns and relationships between students daily habits and their academic performance. The dataset, sourced from Kaggle, includes information on study hours, sleep patterns, diet quality, social media use, and exam results.

This project aims to identify the key factors influencing student exam performance by applying structured data cleaning and visualization techniques. It demonstrates how data-driven insights can be used to better understand academic outcomes and student behavior.

Project Overview

The analysis process involved:

• Loading and inspecting the dataset (CSV format)

• Removing unnecessary columns and handling missing values (replaced with “Unknown”)

• Downcasting data types to improve memory efficiency

• Creating univariate visualizations (histograms and countplots) to explore distributions

• Building bivariate plots (regplots, barplots, and countplots) to examine relationships between variables

• Combining relevant columns to form new derived features

• Conducting multivariate analysis using correlation heatmaps for deeper insights

Technologies Used

• Python: Primary programming language for analysis

• Pandas: Data manipulation and preprocessing

• Seaborn & Matplotlib: Visualization of distributions, relationships, and correlations

Objective

To explore and visualize the relationships between lifestyle habits and exam performance among students, identifying the most impactful behaviors associated with academic success.