Quantifying Holistic Review: A Multi-Modal Approach to College Admissions Prediction
It addresses the problem of fairness and transparency in college admissions for applicants and institutions, though it is incremental as it builds on existing methods like transformers and XGBoost.
This paper tackles the problem of opaque and inconsistent holistic college admissions by introducing the Comprehensive Applicant Profile Score (CAPS), a multi-modal framework that decomposes applicant profiles into interpretable components, achieving an EQI prediction R^2 of 0.80 and classification accuracy over 75%.
This paper introduces the Comprehensive Applicant Profile Score (CAPS), a novel multi-modal framework designed to quantitatively model and interpret holistic college admissions evaluations. CAPS decomposes applicant profiles into three interpretable components: academic performance (Standardized Academic Score, SAS), essay quality (Essay Quality Index, EQI), and extracurricular engagement (Extracurricular Impact Score, EIS). Leveraging transformer-based semantic embeddings, LLM scoring, and XGBoost regression, CAPS provides transparent and explainable evaluations aligned with human judgment. Experiments on a synthetic but realistic dataset demonstrate strong performance, achieving an EQI prediction R^2 of 0.80, classification accuracy over 75%, a macro F1 score of 0.69, and a weighted F1 score of 0.74. CAPS addresses key limitations in traditional holistic review -- particularly the opacity, inconsistency, and anxiety faced by applicants -- thus paving the way for more equitable and data-informed admissions practices.