Skip to content

Simi-Solola/mlbased_tertiaryinstiution_forecast

Repository files navigation

AdmitPredict, an ML-based Nigerian admission forecasting Tool

Background & Motivation

In Nigeria, gaining admission into a tertiary institution can be a long, uncertain journey. For many students, the process is more than just passing exams — it’s a test of patience, resilience, and perseverance. Every year, thousands of hopeful candidates sit for the Joint Admissions and Matriculation Board (JAMB) examinations and complete their West African Examinations Council (WAEC) assessments. Yet, despite hard work, many experience delays, repeated applications, or outright rejections.

I understand this reality deeply — because I’ve lived it.
After completing my secondary school education, I faced an unnecessary and frustrating delay before finally gaining admission into the university. It wasn’t because I lacked ability or passion, but because the system was unpredictable. The uncertainty and wasted time had a profound impact on me, shaping how I view education, data, and decision-making.

This personal experience became my inspiration for this project. I wanted to explore whether data science could be used to bring more transparency to the admissions process — giving students a better sense of their chances and helping them plan accordingly.

Problem Statement

Currently, there is no widely accessible tool that predicts a Nigerian student’s likelihood of gaining admission based on their academic performance and other measurable factors. This leaves candidates in the dark, leading to repeated disappointments, poor planning, and in some cases, loss of motivation.

By analyzing JAMB and WAEC performance data — along with other relevant admission criteria — this project aims to build a predictive model that forecasts the probability of admission.

Project Goal

The primary goal is to use machine learning techniques to:

  • Analyze historical admission patterns in Nigerian universities.
  • Identify the key factors that influence admission decisions.
  • Develop a tool that predicts a student’s likelihood of gaining admission based on their scores and other features.

Beyond the technical challenge, this project is a personal mission:
To ensure that future students don’t have to endure the same uncertainty I did. I envision a platform where prospective undergraduates can input their academic results and other relevant details, and instantly receive a realistic, data-backed prediction of their chances — along with actionable insights on how to improve them.

Expected Impact

  • Students: Gain clarity on their chances and prepare alternative plans early.
  • Parents & Guardians: Make informed decisions about resource allocation and school choices.
  • Policy Makers & Institutions: Identify systemic gaps in admission processes and address them.
  • Researchers & Educators: Access a framework for studying educational outcomes and improving equity.

By reducing uncertainty, we can save students valuable time, reduce emotional stress, and foster a more transparent and data-driven education system in Nigeria.


This project is more than an academic exercise — it’s a commitment to turning my personal challenge into a tool that empowers thousands of students every year.

About

No description, website, or topics provided.

Resources

License

Contributing

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors