0704-883-0675     |      dataprojectng@gmail.com

Evaluation of AI-Based Predictive Models for Identifying University Student Attrition Risks: A Case Study of Usmanu Danfodiyo University, Sokoto (Wamako LGA, Sokoto State)

  • Project Research
  • 1-5 Chapters
  • Abstract : Available
  • Table of Content: Available
  • Reference Style:
  • Recommended for :
  • NGN 5000

Background of the Study
Student attrition or dropout rates have been a longstanding issue for universities, often resulting in significant academic, financial, and social impacts. Understanding the factors contributing to student attrition is crucial for improving retention strategies and ensuring that students complete their academic programs successfully (Adebayo et al., 2023). Traditional methods of predicting attrition primarily rely on historical data such as grades, attendance, and demographic factors, which may not fully capture the complex and multifaceted nature of student attrition (Oloyede & Sulaimon, 2024). However, the use of artificial intelligence (AI) in predictive analytics offers new opportunities to enhance attrition prediction by considering a broader range of factors, including social, psychological, and financial aspects (Ajayi & Aremu, 2025). AI-based predictive models leverage machine learning algorithms to analyze large datasets and identify patterns that can predict student dropout risks with greater accuracy and efficiency (Ibrahim et al., 2024).

Usmanu Danfodiyo University in Sokoto, located in Wamako LGA, Sokoto State, presents a suitable case for exploring the application of AI-based models to predict student attrition. The university, like many in Nigeria, faces challenges with high dropout rates, which negatively impact institutional performance and student success. Several factors, including socio-economic pressures, academic difficulties, and lack of engagement, contribute to the attrition problem (Usman et al., 2023). AI-based predictive models have the potential to identify students at risk of dropping out early, allowing for timely intervention and support to improve retention rates (Baba & Yakasai, 2024).

Statement of the Problem
Usmanu Danfodiyo University has been grappling with rising student attrition rates, which affect not only its financial stability but also the quality of education and institutional reputation. Current strategies for managing attrition rely on basic demographic and academic data, but these approaches often fail to provide a comprehensive understanding of the underlying causes of dropout (Mohammed & Salihu, 2023). The absence of an accurate predictive tool limits the university’s ability to intervene proactively, which is crucial for reducing dropout rates and improving student retention. This study aims to investigate the effectiveness of AI-based predictive models in identifying students at risk of attrition, with the goal of enhancing retention strategies at the university.

Objectives of the Study

  1. To evaluate the effectiveness of AI-based predictive models in identifying students at risk of attrition at Usmanu Danfodiyo University.

  2. To compare the performance of AI-based predictive models with traditional methods of predicting student dropout risks.

  3. To assess the impact of early identification of at-risk students on retention strategies at Usmanu Danfodiyo University.

Research Questions

  1. How effective are AI-based predictive models in identifying students at risk of attrition at Usmanu Danfodiyo University?

  2. What factors are most predictive of student attrition at Usmanu Danfodiyo University?

  3. How do AI-based predictive models compare to traditional methods in predicting student dropout risks?

Research Hypotheses

  1. AI-based predictive models will be more accurate than traditional methods in identifying students at risk of attrition at Usmanu Danfodiyo University.

  2. Factors such as socio-economic status, academic performance, and engagement levels will significantly predict student attrition at Usmanu Danfodiyo University.

  3. The use of AI-based predictive models will lead to improved retention rates through timely interventions at Usmanu Danfodiyo University.

Significance of the Study
This study will provide valuable insights into how AI can be used to predict and prevent student attrition, thus improving retention rates at Usmanu Danfodiyo University. The findings may also guide other Nigerian universities in developing similar models to enhance student success and reduce dropout rates.

Scope and Limitations of the Study
The study will focus on the application of AI-based predictive models to identify student attrition risks at Usmanu Danfodiyo University, Sokoto, located in Wamako LGA, Sokoto State. The study will be limited to students enrolled in undergraduate programs, and data on dropout rates will be collected from the university’s records.

Definitions of Terms

  1. Student Attrition: The phenomenon of students leaving or discontinuing their studies before completing their academic program.

  2. Predictive Models: Statistical and AI-based tools that forecast outcomes, such as student attrition, based on historical and real-time data.

  3. Retention Strategies: Methods and interventions designed to improve student persistence and reduce dropout rates.





Related Project Materials

THE MILITARY AND NIGERIA POLITICS: AN ASSESSMENT OF THE DOMINATION OF THE MILITARY OF THE NIGERIA POLITICAL SPACE 1999 TO 2015

Background of the study

The name “Nigeria” was coined by Flora Shaw, who later became the w...

Read more
The influence of religious education on students’ willingness to support charitable initiatives in Lafia LGA, Nasarawa State

Background of the Study

Religious education is often heralded as a transformative tool that instills not only moral values but also a spi...

Read more
THE IMPACT OF EARLY CHILDHOOD EDUCATION ON SOCIAL JUSTICE AWARENESS

ABSTRACT: The impact of early childhood education on social justice awaren...

Read more
The impact of financial crimes on economic growth in Abakaliki Local Government Area, Ebonyi State

Background of the Study
Financial crimes, including fraud, embezzlement, and money laundering, have far-reaching implicati...

Read more
THE ROLE OF PREDICTIVE ANALYTICS FOR MARKET DEMAND FORECASTING: A CASE STUDY OF KANO’S KURMI MARKET

Background of the Study

Market demand forecasting is a fundamental aspect of effective business planning, particularly i...

Read more
Analysis of Network Downtime Causes in Federal University, Wukari, Taraba State

Background of the Study
Network downtime is a significant challenge for universities, as it disrupts academic activities, a...

Read more
EVALUATION OF THE USE OF TENDERS IN PUBLIC SECTOR PROCUREMENT

ABSTRACT

The subject matter of this study is to carefully evaluate the use of tenders in the public sector procurement....

Read more
A STUDY ON THE STRATEGIES FOR PROMOTING LIFELONG LEARNING HABITS AMONG VOCATIONAL STUDENTS

ABSTRACT: Strategies for Promoting Lifelong Learning Habits Among Vocational Students examines approaches to instill a culture of continuous learni...

Read more
The effect of online security certifications on customer confidence in banking: a case study of Citibank Nigeria

Background of the Study

In the digital banking era, online security is a major determinant of customer confidence. Citibank Nigeria has a...

Read more
EFFECTS OF GLOBALISATION ON HR PRACTICE IN NIGERIA

ABSTRACT

The purpose of this research work on the effects of globalization on human resources prac...

Read more
Share this page with your friends




whatsapp