Application of online MOOC education management technology in learning behaviour mining and dropout prediction

In order to address the issue of low completion rates in MOOC online education, this study uses the K-means clustering algorithm (K-means) model to mine behavioural data of MOOC online learners and improves the K-means model using heuristic methods. In addition, an improved long short-term memory (LSTM) network is used to construct a dropout prediction model. The improved K-means model has improved data mining performance by 4635% compared to the K-means model. Selecting six typical courses in MOOC education for dropout prediction, the improved LSTM model achieved a prediction accuracy of 95.65%, which is superior to SVM and LR models. From this, it can be seen that the proposed method has good application effects, and the research content has important reference value for improving MOOC online education.