Predicting Student Retention: Leveraging Machine-Learning Derived Insights to Improve Student Experience

Understanding the factors that influence student retention is a critical element of providing a high-quality student experience. Machine Learning (ML) techniques give a new means of analyzing this long-standing area of interest.

In this session, we will explore the process of developing a predictive model to identify students at risk of not being retained. We will review the origins of the project, the progress that we have made, and the directions of future work. We will also discuss how the Microsoft Fabric environment provides a single platform for unified data management, constructing ML models, and reporting insights in Power BI.

Learning Outcomes

• How insights acquired from ML models can be used to enhance the student experience.
• Understand student retention better and use this information to improve student experience.
• Gain knowledge about creating ML models to identify at-risk students.
• Learning about the Microsoft Fabric platform where data can be stored, ML models can be built, and results can be visualized in Power BI.