As per an MIT study, the completion rates for LMS-based courses is not more than 4 per cent and the success of the graduates is even lower. Various factors that influence learner engagement include the quality of lesson design and delivery, it’s difficulty for students, or loss of motivation among the learners due to changed priorities. Learning analytics helps identify at-risk learners and provide timely manner interventions, preventing academic failure. Learning analytics is defined as the measurement, collection, analysis and reporting of data about learners and their contexts, for purposes of understanding and optimizing learning and the environments in which it occurs.

Learner behavior data captured in the form of platform interaction, virtual participation, assessment performance etc. gives abundant opportunities to understand learner engagement in quasi real-time. 

One of the most significant benefits of learning analytics is being able to offer support for eLearning experience personalization. This information allows us to recommend supplemental courses or modules to fill performance gaps and improve the comprehension.

BrainAlive’s learning analytics helps build the learner profile, by grouping the user’s data from different sources, by analyzing them and providing a complex result on four levels of the virtual behaviour of the student: the descriptive level (what has happened), the diagnosis level (why it happened), the predictive level (what will happen, for example signaling the lack of performance and the risk of failure) and the prescription level (what should be done, for example the recommendation of educational resources)

Descriptive Analytics

It examines the results and analyzes past events to know how to approach the future. Descriptive analysis looks at past performance and understands the progress by extracting historical data to find reasons for past success or failure. It summarizes the raw data and will display the results in a format easy to interpret by users, allowing them to learn from past behaviours and understanding how it might affect their future performance. Using descriptive analytics, we aim to create the virtual profile of the student, to indicate the current level of performance, describing the previous results and the events that led to these results.

Diagnostic Analysis

Diagnostic analytics providex more information than typical results, by examination of the data content to answer to the question: “Why did it happen?.

The purpose of the diagnostic analytics is to investigate why the user has exhibited a certain behavior.  e.g. a lack of information, a lack of practice or it is an isolated event, produced once, caused by lack of attention .

Predictive Analysis

Predictive analytics turns data into useful information in order to determine the probable future outcome of an event or the probability that a certain situation will occur, answering the question: “What will happen?”. This level of analytics is based on the previous two levels (descriptive and diagnostic), using their results to apply an algorithm of prediction (educational data mining) which will predict the performance of the student based on his behaviour and past results.

Prescriptive Analytics

Prescriptive analytics suggests decision options to take advantage of the predictions, using optimization algorithms to advise on possible outcomes and answer the question: “What should we do?  Based on this analytics, new recommendations will be made so that the student can reach his maximum potential. Teachers will have access to these statistics, to have a clear idea of the performance of their students, having the ability to improve and adapt the content of the future courses.

Categories: Blog

Share via
Copy link
Powered by Social Snap