Prediction of University Comprehensive Score Based on Regression Analysis
- DOI
- 10.2991/assehr.k.220701.050How to use a DOI?
- Keywords
- Machine learning; linear regression; university ranking; prediction
- Abstract
Machine learning [1-5] is regularly accustomed to various fields to resolve troubles that are not able to easily solve in founded on computer methods. The most straightforward and frequent algorithms in machine learning is linear regression. Linear regression is a method for performing predictive analysis based on mathematics. University ranking is a very important but also very challenging and controversial issue. The comprehensive strength of a university involves scientific research, teachers, students and other aspects. But what factors weigh heavily in rankings, and how a university’s composite score is determined based on factors such as education quality, alumni employment, research output and citations. The linear regression is used in this study to forecast the strength of universities based on the rankings of teachers and scientific research provided by CWUR, and explores which factor has the greatest impact on university strength. This dataset [6] comes from Kaggle and contains various metrics and rankings of thousands of universities. After conducting a large number of linear programming predictions and simulations, the data show that Harvard University has the highest overall strength, and the quality of faculty is the evaluation indicator that has the greatest impact on the overall score.
- Copyright
- © 2022 The Authors. Published by Atlantis Press SARL.
- Open Access
- This is an open access article distributed under the CC BY-NC 4.0 license.
Cite this article
TY - CONF AU - Yutong Li PY - 2022 DA - 2022/07/04 TI - Prediction of University Comprehensive Score Based on Regression Analysis BT - Proceedings of the 2022 International Conference on Science and Technology Ethics and Human Future (STEHF 2022) PB - Atlantis Press SP - 244 EP - 250 SN - 2352-5398 UR - https://doi.org/10.2991/assehr.k.220701.050 DO - 10.2991/assehr.k.220701.050 ID - Li2022 ER -