The term Practical Analytics is associated with a range of other techniques and fields of study, including learning analytics, academic analytics, educational data mining and recommended systems.
Learning Analytics: Learning analytics is the collection and analysis of data about students for the purpose of improving teaching and learning. Learning analytics uses data techniques, statistical and visualisation tools and social network analysis techniques to study the effectiveness on the improvement of teaching and learning.
Academic Analytics: This term was developed by Goldstein and Katz and was used to describe the application of business intelligence to higher education. The term was used to describe the scope of how institutions gather, analyse and use data to inform decision making in higher education. The definition was later adapted to focus on increasing student retention and improve learning, teaching and student success. It uses large data sets with statistical techniques and predictive modelling.
Educational Data Mining (EDM): EDM is concerned with developing methods to explore educational data and to better understand students and how they learn. EDM aims to analyse educational data for the purpose of resolving research issues and to understand student environments.
Recommended Systems: Recommended systems collect data about user’s behaviour online so recommendations and conclusions can be made that the user may be interested in.
There is an overlap between the definitions used and it can be difficult to differentiate each field. There are subtle differences in the aims, techniques and methods used in each field. Learning Analytics and EDM are most commonly used in the literature.