Tracing knowledge for tracing dropouts: multi-task training for study session dropout prediction

Seewoo Lee, Kyu Seok Kim, Jamin Shin, Juneyoung Park

Dropout Prediction is a way of measuring engagement in an online learning environment, by predicting the risk of a student leaving a study session. Predicting the dropout of users in our product is crucial to tracking a student’s willingness to study for a certain educational task. To that end, it is important to train Dropout Prediction(DP) with Knowledge Tracing(KT) as a multi-task training methodology to properly assess a student’s knowledge state.


Dropout Prediction predicts the risk of a student leaving an online study session.


Knowledge Tracing models attempt to accurately determine a student’s current knowledge state, such as whether a student may respond correctly to a question
We integrated these two tasks and discovered that the performance of study session dropout prediction has increased, especially when the overall amount of data is scarce. As a result, this study proposes DP combined with KT in situations where we have less access to overall data.


Loading PDF…

Get your score in 40 mins!

Just do 1/4 of a full test and get actionable insights.