This technical paper summarises exploratory analysis undertaken to evaluate the effectiveness of using machine learning approaches to calculate projected completion rates for VET programs and compares with the current Markov chains methodology used by NCVER.
This technical report provides an evaluation of three alternative methodological approaches for calculating completion rate projections for apprentices and trainees.
This paper argues that assessment can play a central role in teaching and learning, and selecting an appropriate mix of assessment strategies can satisfy multiple goals of key stakeholders in vocational education and training. These goals include promoting learning, certifying learning and program evaluation. These objectives must be understood in a broad context delineated by the structures of education systems and of labour markets which, in turn, reside within national policy objectives. Forms of assessment must be consistent with the goals of learning and with a broad range of valued learning outcomes.