This project explores the impact of behavioral, lifestyle, and psychological factors on students' academic performance using Python. The analysis examines how students' study habits: specifically study hours per day, class attendance, extracurricular participation and mental health rating. influence their academic performance, as measured by exam scores The project follows a complete data analysis workflow, including data cleaning, exploratory data analysis (EDA), statistical visualization, and multiple linear regression modeling. The findings provide data-driven insights that can help students, educators, and academic institutions better understand the key factors associated with academic success.
Academic performance is influenced by several interconnected factors beyond intelligence alone. Understanding how behavioral, psychological, and environmental variables affect student achievement can help educators and policymakers develop strategies that improve learning outcomes.
This project uses statistical analysis and machine learning techniques to identify the variables that significantly influence students' exam scores and evaluate their impact using a Multiple Linear Regression model.
- Analyze the factors influencing students' academic performance.
- Perform data cleaning and preprocessing.
- Conduct exploratory data analysis (EDA).
- Visualize relationships between variables.
- Build a Multiple Linear Regression model.
- Evaluate model performance using statistical measures.
- Provide data-driven conclusions and recommendations.
Source: Kaggle
The dataset contains 1,000 observations and 16 variables describing students' demographic, academic, behavioral, and psychological characteristics.
Variables include:
- student_id
- age
- gender
- study_hours_per_day
- social_media_hours
- netflix_hours
- part_time_job
- attendance_percentage
- sleep_hours
- diet_quality
- exercise_frequency
- parental_education_level
- internet_quality
- mental_health_rating
- extracurricular_participation
- Exam Score (Target Variable)
- Python
- Jupyter Notebook
- Pandas
- NumPy
- Matplotlib
- Seaborn
- scipy
- Statsmodels
- Imported the dataset into Python.
- Examined the dataset structure.
- Reviewed data types.
- Generated descriptive statistics.
- Checked for missing values.
- Verified data quality.
- Prepared the dataset for analysis.
- Explored relationships between variables.
- Identified important patterns and trends.
The project includes several visualizations to better understand the dataset, including:
- Distribution plots
- Box plots
- Scatter plots
- Regression plots
A Multiple Linear Regression model was developed to examine the relationship between the predictor variables and students' exam scores.
The regression coefficients, confidence intervals, statistical significance, R², Adjusted R², and F-statistic were interpreted to evaluate the model.
- Study hours positively influenced students' exam performance.
- Previous academic performance was one of the strongest predictors of future exam scores.
- Regular class attendance contributed positively to academic achievement.
- Behavioral and psychological factors collectively influenced students' performance.
- The regression model identified statistically significant variables affecting exam scores.
- The model demonstrated a good overall fit and provided valuable insights into the determinants of academic success.
- Student Academic Performance Analysis.ipynb
- Student Academic Performance Analysis.pdf
- student_performance.csv
- Student-Academic-Performance.png
Future work may include:
- Comparing Multiple Linear Regression with other machine learning models.
- Applying feature engineering techniques.
- Performing hyperparameter tuning.
- Developing an interactive dashboard.
- Deploying the model as a web application.
Abdulmalik Ibrahim
AIM Analytics
Website: https://aimanalytics.carrd.co
LinkedIn: https://www.linkedin.com/in/aimanalytics