euphemyaa/JAMB-performance-prediction-analysis

A data-driven analysis of Nigeria's JAMB exam performance (2020-2025) using Python and machine learning. Identifies key failure factors and predicts success rates through 2030. Includes EDA, predictive modeling, and policy recommendations to improve outcomes. # JAMB-performance-prediction-analysis ## Investigating the Causes of JAMB Failure Rates and Predicting Future Performance Trends (2020–2030) ### 📊 Project Overview Over the past five years, the JAMB examination — Nigeria's standardized university entrance exam — has shown a noticeable trend in fluctuating failure rates. This project aims to explore the root causes behind this trend using data-driven research and build a predictive model to forecast performance trends from 2026 to 2030. ______________ ### 🎯 Objectives • Collect and analyze data from students who sat for the JAMB exam between 2020 and 2025. • Identify socio-economic, academic, and behavioral factors affecting performance. • Build a machine learning model to predict pass/fail outcomes. • Forecast national pass/fail rates up to 2030. • Recommend actionable strategies to reduce failure rates. ______________ ### 🧰 Tools & Technologies • Programming Language: Python • Libraries: Pandas, NumPy, Scikit-learn, Matplotlib, Seaborn • Survey Tool: Google Forms • Visualization Tool: Jupyter Notebook • Version Control: Git & GitHub ______________ ### 🔗 Useful Links for Reference • Cleaned Jamb Data: Link (csv) • Comprehensive Report: Link (pdf) • Jamb Exam Experience Survey (2020 - 2025): Link • Jamb Project Documentation: Link (docx) • Jupyter Notebook: Link ______________ ### 📋 Data Collection Data was collected via a structured online survey distributed to individuals who wrote the JAMB examination between 2020 and 2025. The survey captured: • Demographics (age, gender, state) • Educational background (school type, WAEC scores) • Study behavior (daily hours, study method) • Socio-economic status (parental education, internet/electricity access) • Exam experience (score, attempts, perceived difficulty) • Support systems (mentorship, online resources) ______________ ### Key insights **✅ 1. Pass vs. Fail Rate Distribution** Using a threshold score of 200 to classify exam outcomes, 78.2% of students were cat …