Problem Statement:
The client wanted a platform that would offer adaptive learning techniques to enable individual learners to take the same course in different ways based on their skills and comprehension levels.
Solution:
The team built a platform that models dependencies between skills, sub-skills, misconceptions, and learning objectives, and between content and skills. A data scientist created a model that generated alternative paths for students to complete the course based on their individual competencies and content preferences. The ML algorithm collected evidence data of student engagement and its impact on skill proficiency to continuously improve the learning outcome. The Bayesian Graphical Models – a probabilistic graphical model – was used to represent the dependencies between different variables in the model.
Benefits:
The adaptive learning system offers a personalized learning experience for every learner, leading to increased student engagement and improved learning outcomes. The platform’s ability to generate personalized content pathways based on individual competencies and content preferences allows learners to take the same course in different ways, irrespective of their skills and comprehension levels. Overall, the adaptive learning system provides a more effective and engaging learning experience than the traditional one-size-fits-all approach of MOOCs.
