Background of the Study
Graduate employability is a key indicator of the success of higher education institutions, reflecting the effectiveness of academic programs in preparing students for the job market. At the University of Jos, Plateau State, traditional methods of assessing employability often rely on post-graduation surveys and anecdotal evidence, which are reactive and lack predictive capabilities. Big data analytics offers a transformative approach by integrating diverse datasets—including academic performance records, internship and job placement statistics, employer feedback, and labor market trends—to develop predictive models that forecast graduate employability (Ibrahim, 2023). These models employ advanced machine learning algorithms and statistical techniques to identify patterns and correlations that can accurately predict the likelihood of graduates securing employment in their field of study. By providing real-time insights, big data analytics enables the university to adjust academic programs and support services proactively, thereby enhancing the overall quality of education and better aligning curricula with industry needs (Chinwe, 2024). Moreover, the integration of big data in employability prediction can help identify specific skill gaps, guide career counseling initiatives, and inform strategic partnerships with employers. Despite the significant potential benefits, challenges such as data quality, integration of heterogeneous data sources, and concerns over data privacy remain obstacles to the widespread adoption of these technologies (Adebayo, 2023). This study aims to evaluate the effectiveness of big data analytics in predicting graduate employability at the University of Jos by comparing predictive models with actual employment outcomes, and by providing recommendations for improving data-driven decision-making in graduate support services (Balogun, 2025).
Statement of the Problem
The University of Jos faces challenges in accurately forecasting graduate employability using traditional assessment methods that rely on limited and retrospective data. These conventional approaches do not capture the multifaceted nature of employability, resulting in suboptimal adjustments to academic programs and career services (Ibrahim, 2023). While big data analytics holds promise for developing more accurate predictive models by leveraging diverse data sources, its implementation is impeded by issues such as data fragmentation, inconsistent data quality, and privacy concerns (Chinwe, 2024). The lack of a comprehensive data integration framework further complicates efforts to generate reliable predictions, leading to gaps between predicted outcomes and actual employment rates. Additionally, stakeholders express concerns about the ethical implications of using personal and academic data for predictive analytics, which can affect the trust and acceptance of these technologies among graduates and employers (Adebayo, 2023). Without an effective predictive model, the university struggles to implement timely interventions and strategic adjustments that could enhance graduate employability. This study aims to address these issues by developing and validating a big data analytics framework for predicting graduate employability, comparing its performance against traditional methods, and proposing strategies to improve data integration, quality, and privacy.
Objectives of the Study:
Research Questions:
Significance of the Study
This study is significant as it examines the application of big data analytics to predict graduate employability at the University of Jos, providing critical insights for improving academic programs and career services. The findings will inform policy decisions and enhance strategic planning, ultimately leading to higher employment rates and better alignment between education and industry requirements (Ibrahim, 2023).
Scope and Limitations of the Study:
This study is limited to the evaluation of employability prediction models at the University of Jos, Plateau State.
Definitions of Terms:
• Big Data Analytics: The use of computational methods to analyze large datasets (Chinwe, 2024).
• Graduate Employability: The ability of graduates to secure employment in their field of study (Ibrahim, 2023).
• Predictive Model: A tool that uses historical data to forecast future outcomes (Adebayo, 2023).
ABSTRACT: This study explored the Effects of Early Childhood Education on Social Justice Advocacy. The objec...
Background of the Study
Cross-cultural communication refers to the process of exchanging information and understanding b...
Background of the Study
Renewable energy adoption is recognized as a cornerstone of environmental sustainability, especially in areas wit...
ABSTRACT
The foreign exchange management policy of an economy serves as one of the major factor that co...
Background of the Study
Hausa and Fulani have shared a long history of linguistic and cultural contact in...
Background of the Study
Infertility has emerged as a critical public health issue with profound psycholog...
ABSTRACT
Understanding the dynamism of organizational culture and its relationship to employee performance is very c...
Background of the Study
Social media has profoundly influenced how cultural identity is perceived and expressed, particula...
Background of the Study
Land documentation is a fundamental aspect of property ownership and real estate transactions. In K...
Background of the Study
Gamification—the integration of game mechanics into non-game contexts—is increasingly b...