An Intelligent Rule-Based OBE Framework for Learning Outcomes Monitoring, Analytics, and AI-Agent Accreditation Readiness Evaluation
ID：43
View protection：Participant Only
Updated time：2026-10-04 23:24:16 Views：25
Online
Abstract
Outcome-Based Education requires higher education institutions to demonstrate systematic attainment of course and program outcomes and to use the evidence for continuous improvement. In practice, outcomes data and accreditation documents are often maintained in disconnected spreadsheets and repositories, producing delayed, inconsistent, and difficult-to-audit reports. This paper proposes an intelligent rule-based OBE framework that integrates Course Outcome-Program Outcome mapping, attainment computation, learning analytics, and AI-agent-assisted accreditation readiness evaluation. Transparent institutional rules classify outcomes as achieved, partially achieved, or not achieved, while an AI module analyzes Self-Survey Reports and supporting evidence against uploaded accreditation standards. The AI generates criterion-linked strengths, gaps, readiness rationales, and recommendations but does not make final accreditation decisions. The planned Design and Development Research uses iterative prototyping, expert benchmarking, inter-rater agreement, classification metrics, explainability review, and an ISO/IEC 25010-based system evaluation involving IT experts and academic administrators. The framework is intended to provide an auditable, privacy-aware, and human-governed decision-support environment for OBE, quality assurance, and accreditation preparation.
Keywords
accreditation readiness, explainable artificial intelligence, learning analytics, learning outcomes, Outcome-Based Education, rule-based systems
Post comments