Enhanced Donkey and Smuggler Optimization Algorithm for Holistic Student Admissions in Polytechnics

Abstract

In higher education, college admissions, particularly in polytechnics, require an effective and equitable selection process capable of identifying candidates with both academic qualifications and practical competencies. Traditional methods often rely solely on academic metrics, overlooking essential factors such as technical skills, industry certifications, and relevant work experience. To address this limitation, this paper proposes an Enhanced Donkey and Smuggler Optimization Algorithm (EDSOA), a novel variant of the original Donkey and Smuggler Optimization Algorithm (DSOA). The objective of this study is to develop an optimal student admission process that incorporates holistic selection criteria for ND and HND programs. The EDSOA framework evaluates candidates based on the number of O’level credit passes, sitting numbers, practical skill assessments, industry certifications, work experience, and traditional academic ratings. A case study was conducted in the Computer Science Department of the Federal Polytechnic Ile-Oluji to assess the algorithm’s effectiveness. The algorithm was applied to real admission datasets and compared against existing admission practices. The results demonstrated that EDSOA effectively selected candidates with a balanced combination of academic and practical proficiencies. Additionally, the algorithm aligned well with institutional objectives by favoring candidates possessing both academic potential and technical expertise, thus showcasing its suitability for polytechnic settings. In conclusion, the EDSOA framework significantly improves the admission system by offering an enhanced, holistic approach to candidate evaluation. Its application has the potential to refine selection procedures in polytechnic institutions and other educational domains where practical skills are of critical importance.