Adobe Learning Manager includes a learner homepage, which is modern, more content-driven, and personalized according to a learner’s preferences. AI-based learning recommendations aim to enhance learner engagement and identify and address gaps in learning.
The recommendation algorithm is designed to take in multiple sources of input including Industry data on Job roles, titles and descriptions that Adobe has sourced from its partners. This data is then used to train Adobe’s AI algorithms so that Learning Manager can come up with a map that connects industry aligned skills to job titles and/or designations. This then becomes one input to the recommendation algorithm
Learning Manager then uses topic modeling algorithms to analyze the training content within an account and map them to the skills.
Learning Manager uses peer activity data as another signal to drive the recommendation algorithm in a personalized manner. Activities like enrollment, completion and any explicit feedback provided by learners is used here.
Additionally, Learning Manager uses explicit and implicit information gathered from individual learners to further personalize recommendations. A learner will be able to indicate their areas of interest explicitly through enrollments and Learning Manager will receive this information implicitly based on how the Learner ends up taking up the trainings.
Finally, the Admin will also be able to influence the recommendation algorithm using learner attributes that Learning Manager should look at when defining peer groups, and also by actually highlighting Trainings for specific user groups.