Evaluation of AI-Based Learning Analytics for Student Retention Prediction in Kano University of Science and Technology, Wudil, Kano State
- Project Research
- 1-5 Chapters
- Abstract : Available
- Table of Content: Available
- Reference Style:
- Recommended for :
- NGN 5000
Background of the Study
Student retention remains a pivotal concern for tertiary institutions, with dropout rates posing significant challenges to academic progress and institutional reputation. At Kano University of Science and Technology, Wudil, the use of AI-based learning analytics has emerged as an innovative approach to predicting student retention. By analyzing patterns in student behavior, academic performance, and engagement metrics, AI-based systems can forecast which students are at risk of dropping out, thereby enabling timely interventions (Mustapha, 2023). These systems aggregate data from various sources, including attendance records, assignment submissions, and online learning interactions, to create predictive models that offer valuable insights into student success (Sani, 2024).
The application of AI in learning analytics is founded on the principle of proactive intervention. Early detection of potential dropouts allows educators to implement personalized support mechanisms, such as tutoring, counseling, or academic advising, tailored to the individual needs of students (Ibrahim, 2025). In the context of Kano University of Science and Technology, where resource allocation is critical, the predictive capabilities of AI-based analytics can lead to more efficient use of support services and ultimately improve student retention rates. Furthermore, the continuous evolution of AI methodologies has led to the development of increasingly sophisticated models that can adjust to changing educational environments and diverse student populations (Abubakar, 2023).
The integration of learning analytics into the university’s academic framework is also a response to the increasing digitization of education. As courses are delivered through online and blended learning modes, vast amounts of data are generated that can be harnessed to monitor student engagement and academic progress. The insights derived from these data are crucial for informing policy decisions, curriculum design, and student support initiatives (Yakubu, 2024). Despite the promise of these systems, challenges such as data quality, algorithm transparency, and privacy concerns persist, necessitating rigorous research into their effectiveness. This study, therefore, aims to evaluate the role of AI-based learning analytics in predicting student retention and to identify the factors that influence its accuracy and reliability.
Statement of the Problem
The implementation of AI-based learning analytics at Kano University of Science and Technology faces several obstacles that limit its effectiveness in predicting student retention. A primary challenge is the inconsistency in data quality and completeness across various sources. Inaccurate or incomplete data can undermine the predictive accuracy of AI models, leading to false positives or negatives in identifying at-risk students (Garba, 2023). Additionally, the integration of disparate data systems within the university remains a significant technical hurdle. The lack of a centralized data repository complicates the aggregation and analysis of data, thereby reducing the overall reliability of retention predictions (Adewale, 2024).
Another problem is the limited understanding among faculty and administrative staff regarding the interpretation and use of learning analytics. Without adequate training and support, the insights generated by AI systems may not be effectively translated into actionable interventions (Bello, 2025). There is also the issue of algorithmic transparency, where stakeholders express concerns over how predictive decisions are made and the potential for inherent biases in the models (Chinwe, 2023). Moreover, privacy and ethical considerations in the collection and analysis of student data remain a pressing issue, as the continuous monitoring of student activities could be perceived as invasive (Danjuma, 2024). These challenges underscore the need for a comprehensive evaluation of AI-based learning analytics to ensure that predictive models are both accurate and ethically sound.
This study seeks to systematically investigate these issues by analyzing the effectiveness of current AI-based systems in predicting student retention at Kano University of Science and Technology. By identifying the key factors that compromise the reliability of predictive models, the research aims to propose practical solutions that can enhance the use of learning analytics. Ultimately, addressing these problems is essential for improving student support services and reducing dropout rates, which are critical for the academic success and institutional stability of the university.
Objectives of the Study
- To evaluate the predictive accuracy of AI-based learning analytics in forecasting student retention.
- To identify and address challenges related to data quality and system integration.
- To recommend strategies for improving the interpretation and ethical use of learning analytics in student support.
Research Questions
- How accurate are AI-based models in predicting student retention at the university?
- What are the primary challenges related to data quality and integration in learning analytics?
- How can faculty and administrators be better supported in using learning analytics for intervention?
Significance of the Study
This study is significant because it assesses the effectiveness of AI-based learning analytics in predicting student retention, providing a basis for improved intervention strategies at Kano University of Science and Technology. The insights garnered will guide the optimization of data systems, inform policy revisions, and enhance the ethical application of AI in higher education. By addressing technical and practical challenges, the research aims to contribute to reduced dropout rates and overall student success (Mustapha, 2023; Sani, 2024).
Scope and Limitations of the Study
This study is limited to the evaluation of AI-based learning analytics for predicting student retention at Kano University of Science and Technology, Wudil, focusing exclusively on data quality, system integration, and model accuracy.
Definitions of Terms
- Learning Analytics: The measurement, collection, analysis, and reporting of data about learners to understand and optimize learning and the environments in which it occurs.
- Student Retention: The ability of an institution to retain students from enrollment to graduation.
Predictive Model: A statistical technique using historical data to predict future outcomes.
Related Project Materials
REHABILITATION OF EX-CULTISTS IN TERTIARY INSTITUTIONS
ABSTRACT
The issue of cultism in our higher institutions of learning is such that has reached an alarmi...
An evaluation of personalized digital storytelling on consumer connection: An evaluation of a heritage brand in Kaduna, Nigeria
Background of the Study:
Personalized digital storytelling integrates individual consumer data with compelling narratives to create emoti...
An Assessment of Exclusive Breastfeeding Practices Among Mothers in Kaduna State
Background of the Study
Exclusive breastfeeding (EBF) during the first six months of life is widely r...
The impact of geopolitical strategies on sustainable energy initiatives in Kanam Local Government Area, Plateau State
Chapter One: Introduction
An assessment of the impact of government agricultural policies on rural farmers in Ayedaade Local Government Area, Osun State, Nigeria.
Background of the Study
Government agricultural policies play a pivotal role in shaping the livelihoods of rural farmers,...
THE IMPACT OF GLOBAL TRENDS ON VOCATIONAL CURRICULUM ADAPTATION
Abstract: This research investigates the impact of global trends on vocational curriculum a...
An investigation into the impact of school sports policies on student health in Sokoto South Local Government Area, Sokoto State
Background of the Study
School sports policies have increasingly become central to discussions surrounding student health, as these polic...
An appraisal of trade liberalization’s influence on consumer price stability in Nigeria: A study of the CBN (2000–2020)
Background of the Study :
Trade liberalization involves reducing trade barriers—such as tariffs, quotas, and non‐tariff barriers&md...
An appraisal of the influence of social media on gender identity construction in Nsukka Local Government Area, Enugu State
Background of the Study
Social media has emerged as a powerful force in shaping identity, particularly in the context of gender. In Nsukk...
An Assessment of the Role of Midwives in Reducing Perinatal Mortality in Adamawa State
Background of the Study
Perinatal mortality, which refers to the death of a fetus or neonate within the first week of life, is a critical...
