Steven Ritter, Founder and Chief Scientist at Carnegie Learning, has been developing and evaluating educational systems for over 20 years. He earned his Ph.D. in Cognitive Psychology at Carnegie Mellon University and was instrumental in the development and evaluation of Cognitive Tutors for mathematics. Through leadership of the research department, Dr. Ritter has led many improvements to the use of adaptive learning systems and math education in real-world settings. He is the author of numerous papers on the design, architecture and evaluation of Intelligent Tutoring Systems. He is lead author of an evaluation judged by the US Department of Education’s What Works Clearinghouse as fully meeting their standards and is lead author of a "Best Paper" at the International Conference on Educational Data Mining. |
| Most adaptive systems use some form of mastery learning. Mastery learning was a key component of Bloom’s (1984) goal of producing software that is as effective as a personal human tutor. By some measures, intelligent tutoring systems have achieved parity with personal human tutors (vanLehn, 2011). However, human tutors have a clear advantage over intelligent tutors: they can monitor their instruction and change approaches when a particular strategy fails. Carnegie Learning has been developing techniques to identify when a particular instructional approach fails to produce sufficient learning for a cohort of students. We find that, in complex mathematics topics, 10% of students fail to reach mastery. In this talk, I will describe a technique to rapidly detect when students are likely to fail to reach mastery. This detector can ultimately become the basis for an instructional system that self improves by recognizing situations in which instruction is not effective for some students |
