Technology for Education blog

Student Retention Improved by Big Data Analytics

Written by Isabel Sagenmüller | 13 de septiembre de 2016 12:23:00 Z

To improve student engagement and retention, the input of information in the orientation period is crucial to nurture educational data mining. College enrollments and student recruitment processes are over in the northern hemisphere. Rather, any university campus is currently engaging or preparing orientation programs for undergraduate and graduate students. This implies not only critical levels of logistical preparation, but a very good assessment of what students will need.

The way faculties and administrators address this first phase of the semester is going to be key for student motivation and shaping the way they approach the year. The data received in this period will provide considerable input for academic planning, enrollments, course scheduling, campus management and, especially, entry-level data for retention strategies, to detect and address those students at risk of dropping out early.

The Importance of Early Orientation 

Student orientation helps in the transition of new students and prepares them for their responsibilities. It’s an initiation to the climate of the institution, according to the Association for Orientation, Transition and Retention in Higher Education (NODA). College admissions – and later, student affairs professionals – are key to this endeavor. Dallas Long from Illinois State University says that they "accept that college is a critical period of life during which students discover a meaningful identity and develop core values for how they will perceive and experience their adult lives.

”Therefore, these professionals deliberately create programs, services and experiences

that will advance the students’ growth in one or more dimensions of their lives.” 

People in charge of student affairs are crucial to shaping student information. They can use data to assess trends and improve their work, and their input into the system helps other areas of the university improve student engagement, resource scheduling and campus management. Professor Long says that student affairs professionals are founts of qualitative and quantitative data about student populations and services. For instance, librarians would be interested in whether students have access to computers elsewhere fo resource planning for their own computer lab and workstations. 

Therefore, they are essential in understanding student trends

from the beginning of the year.

Big Data and Predictive Analytics Arrive 

George S. McClellan and Jeremy Stringer explain on the book The Handbook of Student Affairs Administration Handbook of Student Affairs Administration that the use of big data in higher education (or educational data mining) can help student affairs plan programs, outreach services and activities with student attributes in mindFor instance:

  • Preassessment data:  

    Before entering college to help inform faculty and administrators about college students' expectations and assist in the transition to college.
  • Utilization data:

    To understand how much student services are used, assisting with scheduling and outcomes and helping student advisors better.

However, many forget that large institutions such as universities are capable of accumulating vast amounts of (unconnected) information both from inside and outside sources. That is Big dataIts extraction can give us interesting insights, as most information hasn’t been processed.

Even though universities are increasingly analyzing and cross-referencing student, academic, administrative and industry information, analytics needs to go a little bit further.

Experts in IT consulted by Trustee Magazine, from the Association of Governing Boards of Universities and Colleges, say that higher education institutions “need to move from merely collecting data that report past accomplishments to more sophisticated analysis that connects the dots in ways that suggest future action.

“Big data must go through predictive analytics. EduCause explains that predictive

analytics uses various technologies to uncover relationships and patterns on

these large data sources. It doesn’t only include database reporting or statistical

analysis, but machine learning, to detect patterns and actionable insights in the

information". 

In fact, according to The Research & Planning Group for California Community Colleges, the most common use of predictive analytics in universities is the implementation of early warning systems. These rely on data about student behavior and help identify students at risk of dropping out, to target interventions that assist them in completing their course and program of study.

Student affairs professionals are key to generate alarms. Unesco says their services provide “a most critical and valuable early warning system to university management on issues affecting students and their social and learning environments.”

Predictive analytics from the onset of the semester (and before) is critical to improving student retention in higher education. To Professor Long, assessment in student affairs implies collecting data “that provides answers on larger questions – such as why a particular group of students has lower rates of persistence or graduation than other students or why students choose to move out of residence halls after their first year of college.” 

What kind of data would you like to generate in student orientation periods?