“Using the student model and using that historical data, we’re able to predict student performance with very high accuracy,” Neti said. “We can identify at-risk learners before certain patterns set it. It’s similar to healthcare. If a disease has progressed too much, it’s very hard to anything about it. It’s the same with learning styles.”
While IBM’s project is limited to K-12 students for now, Neti said these kinds of systems will be implemented at the higher education level as well.
Indeed, many colleges and universities already utilize Big Data and learning analytics to predict student performance, place students in the right courses, and intervene when a student is struggling with a concept. Use of artificially intelligent course material will only increase over the next five years, the researchers predicted.
“This will follow students through entire career,” Netil said. It’s longitudinal data. It keeps track of all these things that a student has touched. It’s what they are beginning to call ‘career pathways.’ We’ll be able to detect the aspirations of a particular student early and ensure the right learning pathways to help him get there. That’s a long-term process.”
Follow Jake New on Twitter at @eCN_Jake, and join the conversation with #eCNBigData.
- What does higher-ed look like in 2023? - January 5, 2015
- Are ed-tech startups a bubble that’s ready to burst? - January 1, 2015
- Are MOOCs really dead? - August 28, 2014