| Title: |
Predicting College Freshman GPA: A Comparative Study of Traditional and Fairness-Aware Machine Learning Models. Research Report. R2503 |
| Language: |
English |
| Authors: |
Edgar I. Sanchez; ACT Education Corp. |
| Source: |
ACT Education Corp. 2025. |
| Availability: |
ACT Education Corp. 500 ACT Drive, P.O. Box 168, Iowa City, IA 52243-0168. Tel: 319-337-1270; Web site: http://www.act.org |
| Peer Reviewed: |
N |
| Page Count: |
48 |
| Publication Date: |
2025 |
| Document Type: |
Reports - Research; Numerical/Quantitative Data |
| Education Level: |
Higher Education; Postsecondary Education |
| Descriptors: |
College Entrance Examinations; College Freshmen; Scores; Grade Point Average; Prediction; Accuracy; Artificial Intelligence; Test Bias; Justice; Regression (Statistics); Student Subcultures; Student Characteristics |
| Assessment and Survey Identifiers: |
ACT Assessment |
| Abstract: |
This study concludes that traditional logistic regression models, particularly those using ACT Composite scores, tend to demonstrate better fairness metrics across subgroups compared to a fairness-aware machine learning gradient-boosted machine model. The exclusion of race/ethnicity from predictive models does not introduce notable bias and may even enhance fairness, providing a lawful and effective way to evaluate students' potential success in college. The findings suggest that postsecondary institutions should adopt a combined approach using both high school GPA and ACT scores to strike a balance between fairness and predictive accuracy, while being cautious with fairness-aware machine learning models due to their complexity and potential biases. |
| Abstractor: |
ERIC |
| Entry Date: |
2026 |
| Accession Number: |
ED677925 |
| Database: |
ERIC |