This repository hosts a comprehensive data analytics project with a primary specialization in Exploratory Data Analysis (EDA).
While the project encompasses the full data science lifecycle—including cleaning, feature engineering, and predictive modeling—its core strength lies in the rigorous analysis of student behavioral patterns. By deeply investigating correlations and trends, this project uncovers actionable insights into the factors driving academic success.
You can run the entire analysis directly in your browser without any local setup.
| Platform | Link |
|---|---|
| Google Colab | 📂 Open Project Notebook |
The primary goals of this analysis are to:
- ✅ Clean and preprocess raw educational data.
- ✅ Conduct specialized EDA to explore trends in student behavior and study habits.
- ✅ Visualize performance indicators to detect hidden patterns.
- ✅ Detect outliers and significant correlations.
- ✅ Build machine learning models to predict outcomes.
- ✅ Identify key factors affecting academic success.
- ✅ Provide actionable insights for educational decision-making.
We performed a deep dive into the dataset to understand the underlying structure:
- Statistical Summaries: robust mean, median, and distribution analysis.
- Correlation Heatmaps: identifying strong and weak relationships between variables.
- Trend Analysis: mapping behavioral changes against performance over time.
- Outlier Detection: rigorous identification of anomalies in the data.
Rich visualizations were created to communicate findings effectively using Matplotlib, Seaborn, and Plotly:
- Histograms & Boxplots
- Scatter & Distribution Plots
- Pair Plots for feature interaction
- Interactive Dashboards
- Language: Python 3.x
- Data Manipulation: Pandas, NumPy
- Visualization: Matplotlib, Seaborn, Plotly
- Machine Learning: Scikit-learn
- Environment: Jupyter Notebook / Google Colab