IR Analyst Lasell University Milpitas, Texas, United States
Session Abstract: The growth of predictive analytics and machine learning (ML) has transformed higher education research and student success initiatives. However, traditional ML models often operate as “black boxes,” raising concerns about bias, transparency, and accountability in decision-making. Explainable AI (XAI) provides a pathway toward interpretable, transparent, and responsible use of predictive modeling in institutional research and student outcomes. This pre-conference workshop equips participants with conceptual grounding, hands-on experience, and practical frameworks to apply XAI in higher education. Through interactive coding demonstrations and collaborative discussion, participants will learn how to balance predictive accuracy with interpretability to support ethical and effective decision-making.
