Predictive analytics in education

Predictive Analytics in Education: a Compass for Navigating Student Choices

Education is a huge sector, and one that is only going to grow around the world as the number of students increases. The sector is currently worth $5 trillion, with education technology valued at around $250 billion. In 2025, as a result of an extra 500 million K-12 and university age students, the whole sector could be worth $8 trillion.

With the market growing, what is that likely to mean for the amount of choice for students?

In developed and developing economies, the number of schools (K-12) and universities is going to increase. Online, brick-and-mortar, traditional and new educational choices are appearing. Jumping on this trend, older universities in the U.S., UK, and Europe taking advantage of respected brand names to accelerate the launch of new institutions in developing economies.

However, for all of the market and customer benefits of unleashing a world of options, there is an argument to be made that too much choice isn't beneficial for everyone.

The choice paradox in higher education

The choice paradox in higher education
via GIPHY

Any trip to a supermarket or corner store will present the average customer with dozens of options. Dark, milk and white chocolate. With nuts and without. Various sweets and other crunchy delights mixed in. Vegan and vegetarian options are also available.

But when it comes to higher education, this isn't as simple as a cheap, forgettable, albeit tasty consumer purchase.

Committing to a university is a very expensive investment (often tens of thousands of dollars). No matter how or when this is actually paid for, a university education is a serious investment that can have a profound long-term impact on the earning potential, disposable income (cost of student loans), and life/career choices of students long after an education is finished. Education itself is a multi-year commitment, with a minimum of between two and four years, although some courses take longer, or are done part-time alongside work and family.

Hence the fact that time ought to be taken to pick a university carefully. It isn’t as simple as picking a chocolate bar, or even a car. A university is almost certainly going to have a bigger impact on someone’s life than what car they buy. So, how can we solve this choice paradox?

How to solve the higher education choice paradox?

Solving the higher education choice paradox
via GIPHY

Traditionally, trying to pick the right university starts with brochures, and websites, and visiting institutions, if a student, or student’s parents have the time/money to visit options. Even when a student is going to study online and through other distance learning mediums, choices need to be reviewed manually.

As the amount of choice increases, not only does this become more difficult, but there is a risk that some potentially good choices could be missed and overlooked. In education, the risk is that selection bias will encourage applicants to only look at those with the well-known brand names instead of exploring a wider set of options.

One of the most effective ways to solve selection bias is with predictive learning and other machine learning-based recommendation systems.

Role of predictive analytics in education

Role of predictive analytics in education
via GIPHY

1. Students and parents:

  • Making the multiple layers of choices easier to define and understand;
  • Reduce the risk of dropping out, or wasting time/money doing a course, or even modules that aren't suitable;
  • Helps show which higher education institutions are value for money, are better for long-term career goals and earnings, and result in higher levels of student satisfaction.

Although there are various apps around - either free or cheap for parents and students - there still isn't enough data without university participation in generating data for future students and other stakeholders.

However, as this is an area of government concern, in the U.S. and other countries, it could soon be the case that universities will need to contribute data to publicly available platform, effectively ‘open-sourcing’ university results and outcome data.

2. Universities and educators:

  • More easily see which courses are doing well, and which aren’t, and then make corrective changes to how courses are delivered to improve educational outcomes;
  • Demonstrate the ROI of courses (e.g. learning outcomes, earning potential, and other key metrics) to appeal more widely to students and parents;
  • Alter brand bias. Newer institutions, including online ones can effectively demonstrate why they're a good investment. Whereas older institutions can demonstrate that they're more than a well-known brand name, thereby allowing a more level and competitive playing field.
  • Lesser known universities can also use predictive analytics as a chance to increase name recognition and demonstrate how they perform compared to those with more established brand names.

Connecting the dots

Predictive analytics and other data-based learning systems are going to play more of an important role in higher education in the years ahead. Students, parents and governments are asking for increased data openness and transparency. Universities themselves will benefit enormously, using this as a way of matching students with courses more effectively and showcasing strengths to a wider and more appreciative audience.



About author: Dariya Lopukhina is an online marketer, tech enthusiast and writer. She is a part of the Anadea team where we help EdTech entrepreneurs, startups and companies digitally transform and grow. Connect with her on Twitter and LinkedIn.