An adaptive learning architecture for the Open edX platform has been tested in the last months by a research group led by Harvard University and Microsoft.
This project, called ALOSI (Adaptive Learning Open Source Initiative), is based on creating an open source adaptive engine powering individualized learning and assessment pathways. This software includes the Bridge for Adaptivity and the ALOSI adaptive engine, two applications supporting a common framework for experimentation that integrates several modular components.
The ALOSI architecture integrates seamlessly via LTI with edX, Canvas and other LMS’s as well as independently with content repositories. ALOSI uses Bayesian Knowledge Tracing—a machine learning algorithm—to power the individualized pathways.
During the 2018 Open edX Conference, Andrew Ang, a research data engineer from Harvard University, will show this modular architecture for adaptive learning.
Mr. Ang will demonstrate the use of this system with the Microsoft MOOC on edX, “Essential Statistics for Data Analysis Using Excel”, and how the mentioned research group used various advanced features of Open EdX (LTI provider, course blocks API, import/export, content experiments).