Article Per Year (5 Year)
p-Index From 2021 - 2026
0
P-Index
This Author published in this journals
All Journal Journal of Applied Artificial Intelligence in Education
Wesolowski, Brian
Unknown Affiliation
Computer Science & IT Education

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search
Journal : Journal of Applied Artificial Intelligence in Education

 1 
Applying Random Forest Machine Learning to Predict Opportunity-to-Learn Classifications in Instrumental Music Education: Toward Data-Driven Equity and Inclusion in Arts Programs Wesolowski, Brian
Journal of Applied Artificial Intelligence in Education Vol 2, No 2 (2027): January 2027
Publisher : Academic Bright Collaboration

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.66053/jaaie.v2i2.437

Abstract

This study applied Random Forest machine learning to predict opportunity-to-learn (OTL) classifications for secondary instrumental music programs using person–item interaction measures derived from a multifaceted Rasch partial credit model. Drawing on a national sample of 374 music educators in the United States, the Random Forest model demonstrated strong predictive performance, achieving an out-of-bag error rate of 13.3% and an overall accuracy of 87%, with cross-validated accuracy estimates showing comparable results. A multinomial logistic regression baseline achieved substantially lower accuracy (62%), confirming that the Random Forest captured a nonlinear structure not recoverable through linear classification. Variable-importance analyses identified curricular, staffing, scheduling, and resource indicators that most reliably distinguished among the three empirically derived OTL classes. The consistency of these results across multiple validation procedures demonstrates that the model effectively captures the underlying structure of OTL conditions and highlights a concentrated set of structural indicators that exert the strongest influence on classification outcomes. By translating complex survey data into a predictive framework, this study offers a foundation for future work aimed at developing scalable, data-informed tools for understanding structural OTL conditions in music education, specifically, and the related arts and sciences, more broadly.
Co-Authors