Modelling Memory Retention Curves

An online language-learning platform seeking to transform adaptive learning.


When a student is taught a word in a foreign language, the likelihood of them recalling the meaning when tested decreases with time. It is well known that reinforcement is key to committing the word to long term memory - the question is: at what points in the future should this be done? Wait too long before reinforcing and the student will never learn; reinforce too soon and you waste valuable learning time and risk boring the student with material they already know.


The client already used memory retention curves from academic literature in their product, but wanted to develop models that more accurately matched the data that they had. The data available for the project was rich, with learning events from over 300,000 users. In addition, the client wanted to classify the users into different groups in order to tailor the learning experience for individual users.

Memory retention curves from academic literature were quickly shown to be poor matches for the data provided by the client. A Random Forest machine learning algorithm produced a model with a much stronger fit, enabling us to begin classifying users into groups. Fast-learning and slow-learning groups were identified.

Modelling Memory Retention Curves
While the “actual data” is taken from the learning of one word, “étude”, the Random Forest model is generalisable to any word.


The new models provided by ASI have significantly more predictive power than those used before. Accurate identification of a student’s group will enable them to learn a language faster.

How can we help?

Get in touch now to find out what our team can do for you.

Contact us

Case Studies