Scriyb’s System and Method for using controlled virtual student grouping, dynamic regrouping, and Deep Academic Learning Intelligence (DALI) academic advising, mentoring, and counseling to scale personalized learning opportunities and improve student academic outcomes.
Learning management software systems, business conferencing software, and MOOCs employed to offer online degrees, courses, and seminars experience higher student attrition rates, and lower student academic achievement outcomes than traditional classroom learning models (Biwa, 2016, Tyler-Smith, 2006). Although new interactive forums and devices, as well as analytics and assessments tools are being overlaid and integrated into LMS platforms to better provide student-to-student and student-teacher interaction, and to measure, track, and assess student performance, online student learning outcomes still fall below traditional on-site classroom results. Moreover, current learning systems are difficult or impossible to scale and maintain quality and integrity of instruction, not to mention provide the necessary academic support resources for larger numbers of online students (Moloney et al, 2010). Lastly, software learning systems are not designed to allow the inherent collating, indexing, analysis and assessment of learning data to provide personalized learning solutions to individual students nor teams of students (Ross, 2016). Scriyb includes a series of inter-related and integrated learning engineering inventions that collectively solve the problems outlined above, and can provide evidence from these inventions of improved student academic outcomes. The series of learning inventions first virtually group students based on predetermined variables, and walls off each group from every other group within the same course of instruction. Follow-on inventions then track, measure, and analyze each student’s academic achievement rates within a communication styles and social theory matrix, dynamically re-balances each virtual group, and deploys intelligent AI (deep neural network) algorithms to provide academic advising, personal mentoring, and counseling channels to consistently guide the student, and optimize their learning environment throughout an academic experience.