University Student Management Effectiveness Based on Artificial Intelligence and Neutrosophic Distributional Uncertainty Modeling

Abstract

Effective university student management is critical for academic success, resource 
optimization, and student retention. Traditional artificial intelligence (AI) systems rely 
heavily on deterministic or probabilistic models that assume known data distributions. 
However, in dynamic and uncertain academic environments, such assumptions often lead 
to inaccurate decisions. This paper introduces a novel modeling approach based on 
Neutrosophic Distributional Uncertainty (NDU), a newly formulated framework where 
the probability distribution governing a student's academic performance is treated as a 
neutrosophic variable with inherent truth, indeterminacy, and falsity degrees. By 
integrating this concept into an AI-based student management system, we propose a new 
decision-making model that quantifies uncertainty not just in outcomes but in the 
underlying statistical models themselves. This approach enables adaptive decision
making under distributional ambiguity. The proposed model is validated with 
hypothetical academic performance datasets, and results show that it significantly 
enhances prediction stability and management accuracy compared to classical statistical 
or machine learning systems. 

DOI: 10.5281/zenodo.16754907