Towards Automatic Training Design

Abstract

With the emergence of a knowledge driven economy, these are times of brisk business for institutions providing training to professionals. The flipside of this is that there is an ever increasing demand on them to create a growing number of new courses, and serve an ever increasing flow of customers ata faster and faster pace. In its various flavours, this problem is faced by MOOC/online course providers, training departments of large organisations, and modern universities which offer short term courses for corporate audience as well. Hence, there is a need to optimally utilise all available resources: time of trainer/trainee/organisation, infrastructure etc. while designing and conducting training courses. Current practice is to do thismanually. In this paper, we build a case for automation of this process. We present mathematical models for 3 problems in this space. Once a mathematical model of a problem is developed, it becomes possible to carry out several analyses on these problems, design automated solutions. As is revealed from the mathematical models, the problem of training curriculum design has already grown beyond the complexity that a human expert can handle efficiently. With every passing day, the gap will only increase. Our simulations establish the efficiency and effectiveness of the solutions we provide.