Education
❯
Personalized Learning
❯VTrain recommendation engine
AI adaptive learning platform for personalized learning
For:
Students, teachers (content providers), third-party services (via experience API),
academic researchers (sets of eduDATA)
Scope:
2,5 million users [247]
Goal:
Improved Customer Experience
VTrain recommendation engine
For:
Employees, job requirements, training requirements
Scope:
Find skill requirements and relevant training based on an employees career
objectives.
Goal:
Improved Customer Experience
General Public
Education - Personalized Learning
For:
Foreign language learners
Scope:
Keeping foreign language learners engaged with Deep Learning in the Duolingo app.
Goal:
Improved Customer Experience, Increase Revenues
AI solution to intelligent campus
For:
Students, teachers, schools, governments
Scope:
This scheme is a full range of products and integrated solutions for teaching, examination, evaluation, management, and learning.
Goal:
Improved Employee Efficiency
VTrain recommendation engine
For:
Employees, job requirements, training requirementsGoal:
Improved Customer ExperienceProblem addressed
Recommend a personalized list of best training courses to an employee, which
would help him/her meet his/her career objectives.
Scope of use case
Find skill requirements and relevant training based on an employees career
objectives.
Description
Continuous training is crucial for creating and maintaining
the right skill profile for an industrial organizations
workforce. There is tremendous variety in the available
training within an organization: technical, project
management, quality, leadership, domain-specific, soft-
skills, etc. Hence it is important to assist the employee in
choosing the best training that perfectly suits his/her
background, project needs and career goals. In this work, we
focus on algorithms for recommending training in an
industrial setting. We formalize the problem of the next
training recommendation, taking into account the
employees training and work history. We have developed
several new unsupervised sequence mining algorithms to
mine past training data from the organization for making the
next personalized training recommendation. Using real-life
data about training 118 587 employees over 5 019 distinct
training courses from a large multi-national IT organization,
59
we show that these algorithms outperform several standard
recommendation engine algorithms as well as those based
on standard sequence mining algorithms.