Download

Download Full Text (364 KB)

Description

This project explores how multimodal, fairness-aware machine learning models can enhance early prediction of student success while promoting equity in higher education. Traditional prediction models often rely on static academic or demographic data, which can unintentionally reinforce bias and overlook the complex, behavioral aspects of learning. Our approach integrates engagement metrics from learning management systems, academic performance data, and motivational survey responses to capture a more holistic view of student learning. The predictive framework emphasizes behavioral and psychological features that are both actionable and ethically sound, supporting real-time intervention through the iTOOLS platform. By focusing on engagement consistency and motivational indicators, the model enables advisors to identify and support at-risk students earlier in the semester. The long-term vision extends beyond prediction toward creating proactive, data-informed advising systems that improve retention, promote fairness, and strengthen institutional decision-making. This work contributes to UNLV’s broader effort to build transparent and responsible AI systems that empower educators and advance student success across diverse learning contexts.

Publisher Location

Las Vegas (Nev.)

Publication Date

Fall 11-21-2025

Publisher

University of Nevada, Las Vegas

Language

English

Keywords

Machine Learning; Education; Predictive Analytics; Student Success; AI

Disciplines

Educational Leadership | Educational Psychology | Higher Education

File Format

PDF

File Size

319 KB

Permissions

Google Drive\Institutional Repository\OUR_OfficeOfUGResearch\Symposia\2025 Fall Symposium

Comments

Mentor: Jonathan Hilpert

Rights

IN COPYRIGHT. For more information about this rights statement, please visit http://rightsstatements.org/vocab/InC/1.0/

Enhancing Student Success Prediction with Multimodal Machine Learning Models


Share

COinS