INTO, a global leader in international education services, has introduced a groundbreaking AI model aimed at predicting and minimising student melt in university admissions.
This AI-driven tool is part of INTO’s broader efforts to enhance the admissions process through artificial intelligence, improving recruitment, retention, and institutional efficiency.
Student melt—where students fail to proceed with enrolment despite confirming their place—can have significant consequences for universities. INTO’s machine learning model delivers accurate predictions and practical insights, allowing institutions to proactively manage and reduce melt rates.
With INTO’s existing AI-powered admissions solutions, application processing times have already been cut from weeks to hours. This new development further expands its suite of AI-enhanced education services.
“This new machine learning model represents a significant leap forward for the higher education sector in managing student enrollment,” said Andy Fawcett, INTO’s Chief Technology Officer and Executive Vice President of Global Admissions.
“With precise forecasts and actionable insights, we are equipping universities with the tools they need to navigate the complexities of student retention and enhance their financial performance.
“By analysing a vast array of data points, the system delivers precise predictions and enables institutions to proactively address student needs. This proactive approach helps universities optimise their resources and strategies, ensuring a more efficient and effective enrollment process.”
- Advanced precision forecasting: The model uses sophisticated algorithms to categorize students into various risk bands, ranging from “rare chance” to “almost certain” to melt. By analyzing over 70 different data points, including unique factors such as student visa status and visa preparedness, the model delivers precise forecasts that enable institutions to plan more strategically.
- Granular data analysis: The model allows institutions to drill down into individual student data and specific institutional patterns, offering actionable insights to identify high-risk areas and allocate resources where they are most needed.
- Real-time updates and validation: The system is updated daily with live data, providing the most current predictions and validating them against actual outcomes, ensuring accuracy and enabling continuous refinement.
- Actionable insights for effective interventions: Beyond forecasting, the model identifies students at risk of melt and provides strategies for personalized interventions such as outreach or visa support, enabling institutions to address issues proactively.
