Higher education has evolved to be a data informed industry. Many institutions have implemented data analysis for decision-making after having been an anecdote driven industry for decades. It’s a great evolution in higher education’s data journey. Even with predictive analytics in place, however, that’s not enough to know how to support students.
Predictive analytics can tell you the “what”: is a student going to enroll next term? Are they at risk of stopping out? Will they graduate?
But what predictive analytics doesn’t do is tell you why or what to do about it.
What predictive analytics does
Predictive analytics is the use of historical data to predict future outcomes. In higher education, institutions use predictive analytics to predict which students will enroll, how likely a student is to persist through the next term, or if a student will graduate, among other outcomes. Institutions use several data points to do this. Often, demographic data is also part of the equation even though it is not the best data for predicting outcomes. Predictive analytics is a helpful tool for identifying students who may be struggling, especially if they would go otherwise unseen. But it misses a really important piece.
What predictive analytics misses
Imagine that an advisor receives an alert on their CRM that tells them that a student is at risk for attrition. The advisor would likely reach out to the student to offer support. It’s unlikely the advisor has a strong relationship to the student due to a high caseload, so the advisor would have to dig to figure out why a student is at risk of stopping out. Is it because they are a first-generation student or because they feel like they don’t belong? How should the advisor engage with the student, or what resources should they recommend?
With predictive analytics, the advisor won’t know the real reason the student is at risk unless they reach out to the student. The student would also have to respond to the advisor’s outreach and follow a series of steps to actually connect with an advisor. This can be challenging for today’s busy students.
That’s where prescriptive analytics comes in.
What is prescriptive analytics?
Prescriptive analytics helps users determine what actions to take on a prediction. While predictive analytics addresses what might happen in the future, prescriptive analytics takes things to the next level because it answers what should be done next. Prescriptive analytics combs through data to make recommendations based on specific requirements and has several benefits for organizations.
Educators can support students more efficiently and effectively with prescriptive analytics because they receive guidance on how to help a student. This method can augment educators’ ability to help students because it suggests a course of action based on a predicted outcome. For example, an advisor could more easily identify students who are struggling and automate connecting that student to a helpful resource. That way the advisor can spend time connecting with more students or focusing on high needs cases.
How Discourse Analytics uses AI to enhance prescriptive analytics
Predictive and prescriptive analytics can be augmented with the use of AI to automate calculations and outcomes. Discourse Analytics’ AI enabled model uses behavioral data to identify student mindsets and the best engagement strategy based on that mindset. This empowers educators to identify what motivates and discourages a student. They can also provide resources tailored to student needs instead of taking a one-size-fits-all approach to increase student success.
Knowing the difference between predictive analytics and prescriptive analytics is important because it can unlock another level of analysis for institutions. Prescriptive analytics allows institutions to address student outcomes head on instead of being left wondering what to do.
Want to see how we can help you personalize learning experiences? Contact us here.