Educational Data Minding (EDM) has been defined as “an emerging discipline, concerned with developing methods for exploring the unique types of data that come from educational settings, and using those methods to better understand students, and the settings which they learn in.” (International Society of EDM).

An extensive overview of EDM applications, developments and definitions has been given by Baker and Yacef (2009). EDM has its origins in multiple research areas such as statistics, data mining, machine learning, visualization and computational modelling aiming to automatically discover patterns and models from huge and extensively growing datasets. While in the beginnings of EDM, most data was retrieved from experimental learning sets not lasting longer than a couple of weeks, nowadays such data is often tracked over the duration of a whole course lasting up to one study year. Collected data is further analysed to gain valuable insights on learning processes and aspects. With  these enormous  loads of data  new challenges arise

Learning Analytics especially emphasises on supporting pedagogical approaches by providing assistance to teachers in practically relevant questions (e.g., the quality of learning material or the engagement of students in specific exercises). Data gained by LA tools can be used to evaluate pedagogically sound instructional designs within classroom settings. In most cases this focuses mainly on monitoring learner actions and their interactions with learning tools and learning peers (Lockyer & Dawson, 2011). Many attempts go towards visualizing these learning traces in order to make significant relationships explicit or even to allow stakeholders to discover such relations independently. Research using dashboards in LAs has been described by Duval (2011). As known in other domains like for instance sports, the visualization of collected interaction training data and the comparison with of this data with data of like-minded peers, may lead to insights about unwelcome habits and better practices but also to higher motivation due to the playful introduction of competitiveness. Dychkoff et al. (2012) describe a learning analytics toolkit that takes a step forward by allowing the course instructors to define their own learning indicators via combining traced student actions. This toolkit is designed to support the instructors in optimizing their teaching strategies. An example of inferences drawn from the learning indicators about the quality of teaching material is the relation between time spent on specific learning objects and learning outcome. Also hardly touched learning objects can be assumed of poor quality with respect to the learning audience.

The future of TEL is often seen in flexible, teacher or even learner composed mash-up learning frameworks, independent of a specific environment (Chatti et al., 2010). To keep up with this development new learning analytics toolkits need to be just as flexible and adaptable as learning tools.