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

by 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 min!

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

R.test is an AI-powered diagnostic test platform that evaluates student’s test readiness. Our mission is to get rid of inefficiency and inequality from test prep industry by making assessments more adaptive, accessible, and reliable.

â“’ 2023 Riiid, Inc. All Rights Reserved

521, Teheran-ro, Gangnam-gu, Seoul, Korea

College Board® is a trademark registered by the College Board, which is not affiliated with, and does not endorse, this website.

Neither Riiid, Inc. or R.test is affiliated with College Board® and do not have access to College Board's proprietary data.

ACT® is a registered trademark of ACT, inc. This website is not endorsed or approved by ACT, inc.

Neither Riiid, Inc. or R.test is affiliated with ACT, Inc. and do not have access to ACT’s proprietary data.