Work

DMP: University Ranking Comparison

Year: 2025

Type: article

Abstract: This project explores whether machine learning models trained on data from one university ranking system (e.g., QS, ARWU, THE) can accurately predict the rankings of another system, or whether valid results are only achievable when training on the specific ranking’s own data. Random Forest models were developed using standardized performance indicators, and their predictive performance was evaluated across multiple ranking datasets. The outputs include trained models, evaluation results, and prepared train/test datasets for reproducibility and further analysis. Github: https://github.com/kutq/UniversityRankingComparison DBRepo: https://test.dbrepo.tuwien.ac.at/database/1b5ad9c5-c3fa-42ae-975b-19ee5ef679bd/info TUWRD: https://test.researchdata.tuwien.ac.at/doi/10.70124/66hd7-wzm39

Source: Zenodo (CERN European Organization for Nuclear Research)

DOI: 10.5281/zenodo.15298267

Author: Kutscher, Tobias

Language: English

Topic: Higher Education Governance and Development

Subfield: Political Science and International Relations

Field: Social Sciences

Domain: Social Sciences

Open Access status: green

OpenAlex ID: W6949406540

FWCI:

Cites:

Cited by:

Related to: