Purdue University Achieves Remarkable Results With Big Data
Purdue University, a university located in West Lafayette, Indiana, has over 40.000 students and 6.600 staff members. It was founded in 1869 and it recently was honoured America’s most innovative campus retention program. Purdue University is ready for the future since its adoption of big data. In a recent post I wrote about the tremendous opportunities for big data in the educational field, although academia are not known for being early adopters. Purdue University, however, is applying big data and achieves significant results.
Purdue University developed Course Signals, a system that helps predict academic and behavioural issues and notifies teachers as well as students when action is required. The system ensures students achieve their maximum potential as well as it decreases dropouts and failing rates. The platform has been very successful and even won the Lee Noel and Randi Levitz Retention Excellence Awards in 2012. Course signals is generally viewed as the best practice how analytics can be applied in higher education to help improve student results to help them graduate in a timely manner.
Course Signals combines predictive modelling with data mining on Blackboard. It uses various sources of data such as student information and course management systems. Already as of week two in a semester, this data mining tool is able to understand a student’s academic preparation, engagement in and effort within a course and academic performance at a given point in time. It uses student characteristics and academic preparation, the effort students put into the course (sessions, quizzing, discussions as well as time required to perform a task) and student (past) performance (grades received so far and book data).
The algorithm predicts for each student a risk profile based on an easy to understand system: green (there is a high likelihood of success in a particular course), yellow (there are potential problems) and risk (there is a risk for failure). The fact that this prediction is provided already in week 2 of a semester gives the students ample opportunity to improve their results.
Course Signals provides the teachers with feedback when they run the software, enabling the teachers to follow-up with the students instantly when problems might arise. Teachers can run the software as often as they want, but only when it is ran the prediction gets updated. Immediately the system provides the students with various resources that can help them improve in the course. The risk profile can be adjusted per course, depending on what the teachers deems fit.
The below video explains Course Signals in more detail:
The system has been in use already since 2007 and the results are remarkable: improved grades for students and higher retention rates. As the website of Course Signals mentions: “As and Bs have increased by as much as 28% in some courses. In most cases, the greatest improvement is seen in students who were initially receiving Cs and Ds in early assignments, and pull up half a letter grade or more to a B or C.”
In addition to Course Signals, Purdue University has partnered with EMC to solve their big data problems. All 40.000 students will receive 100 Gigabyte of storage space (that is four petabyte of storage) and they will work together to develop new ways to process, analyse, transfer and manage the massive research data sets, among other in the field of bioinformatics.
It may be obvious that Purdue University has identified big data as very important for research and education. They are currently recruiting several faculty positions to stimulate and further develop the big data agenda. Purdue University is far ahead compared to other educational institutes in adapting and implementing a big data strategy. With their expansion of the faculty we can expect a lot more in the coming years.
Image Credit: Stephen+B.+Goodwin/Shutterstock
Sign in or become a The Digital Speaker - Future Tech Strategist member to join the conversation.
Just enter your email below to get a log in link.