University Rankings Prediction Using Hybrid Feature Selection Based on Machine Learning Methods
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
This study presents a novel approach to predicting university rankings using hybrid feature selection and machine learning techniques. It identifies critical performance factors that affect ranking accuracy using the Times Higher Education (THE) dataset, which includes data from 1,904 universities. A Max-Min normalization method and an artificial neural network were applied to preprocess the data. Then, a hybrid feature selection method, combining statistical and machine learning techniques, was used to determine the optimal feature subsets. Several prediction models, including linear regression, random forest, and multilayer perceptron, were evaluated and compared based on various metrics: accuracy, precision, mean absolute error (MAE), root mean square error (RMSE), and R². The results indicate that hybrid feature selection using machine learning significantly enhances predictive accuracy. The hybrid model consistently outperformed all other models across various metrics, achieving the highest accuracy (0.971), precision (0.985), recall (0.971), and F1-score (0.972). These results demonstrate that the hybrid model effectively balances true positive and false positive predictions while minimizing errors. Furthermore, the error metrics for the hybrid model were the lowest among all models, with an MAE of 0.034 and an RMSE of 0.028. This reinforces its superiority in delivering highly reliable predictions. This study demonstrates the effectiveness of hybrid feature selection in refining ranking systems and offers a robust framework that can be applied to various datasets and ranking environments. The findings provide valuable insights for improving ranking predictions and shaping strategies in higher education.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it