Mining Meta-indicators of University Ranking: A Machine Learning Approach Based on SHAP

TL;DR

This paper uses interpretable machine learning to identify three key meta-indicators—time, space, and relationships—that simplify the complex system of university rankings.

Contribution

It introduces a novel approach to extract meta-indicators from complex ranking systems using SHAP-based interpretability methods.

Findings

Identified three meta-indicators: time, space, and relationships.

Demonstrated the effectiveness of machine learning in simplifying university rankings.

Provided insights into factors influencing university evaluation metrics.

Abstract

University evaluation and ranking is an extremely complex activity. Major universities are struggling because of increasingly complex indicator systems of world university rankings. So can we find the meta-indicators of the index system by simplifying the complexity? This research discovered three meta-indicators based on interpretable machine learning. The first one is time, to be friends with time, and believe in the power of time, and accumulate historical deposits; the second one is space, to be friends with city, and grow together by co-develop; the third one is relationships, to be friends with alumni, and strive for more alumni donations without ceiling.