Date
Publisher
arXiv
Academic performance depends on a multivariable nexus of socio-academic and
financial factors. This study investigates these influences to develop
effective strategies for optimizing students' CGPA. To achieve this, we
reviewed various literature to identify key influencing factors and constructed
an initial hypothetical causal graph based on the findings. Additionally, an
online survey was conducted, where 1,050 students participated, providing
comprehensive data for analysis. Rigorous data preprocessing techniques,
including cleaning and visualization, ensured data quality before analysis.
Causal analysis validated the relationships among variables, offering deeper
insights into their direct and indirect effects on CGPA. Regression models were
implemented for CGPA prediction, while classification models categorized
students based on performance levels. Ridge Regression demonstrated strong
predictive accuracy, achieving a Mean Absolute Error of 0.12 and a Mean Squared
Error of 0.023. Random Forest outperformed in classification, attaining an
F1-score near perfection and an accuracy of 98.68%. Explainable AI techniques
such as SHAP, LIME, and Interpret enhanced model interpretability, highlighting
critical factors such as study hours, scholarships, parental education, and
prior academic performance. The study culminated in the development of a
web-based application that provides students with personalized insights,
allowing them to predict academic performance, identify areas for improvement,
and make informed decisions to enhance their outcomes.
Study at a glance
- Question: Which socio-academic and economic factors causally influence and best predict university students' CGPA?
- Setting and data: Online survey of 1,050 university students aged 18 or older in Bangladesh, approved in February 2025.
- Method: Machine learning prediction, causal discovery algorithms, and explainable AI techniques (SHAP, LIME, Interpret).
Why it matters
In Bangladesh's competitive education system, academic performance models often overlook non-academic factors, dynamic influences, and model explainability, limiting actionable guidance for students and educators.
Key findings
- Random Forest achieved the best classification performance for CGPA levels with 98.68% testing accuracy, while Ridge Regression produced the lowest prediction error among regression models.
- Causal discovery and explainable AI models identified weekly study hours, scholarship receipt, father's education, and prior secondary school results as primary drivers of academic performance.
- Descriptive analyses showed that students living in hostels studied fewer weekly hours, while higher-income students reported greater self-confidence across decision-making and academic activities.
Summary drafted with AI from the full paper and may contain errors. See the full paper for details.
What is the application?
Who age?
Why use AI?
