Applying machine learning technologies to explore students' learning features and performance prediction.

Area of Science:

• Educational technology
• Computer science
• Data science

Background:

• Understanding student learning behaviors is crucial for improving educational outcomes.
• Interactive learning environments generate valuable data for analysis.
• Predictive modeling can offer insights into student performance.

Purpose of the Study:

• To apply machine learning techniques to analyze student data from interactive learning environments.
• To predict student learning outcomes, specifically on-time submission.
• To identify correlations between learning characteristics and performance in programming practice.

Main Methods:

• Utilized machine learning classification algorithms: Random Forest (RF), Support Vector Machine (SVM), Logistic Regression (LR), and Neural Network (NN).
• Analyzed data from interactive learning environments, including quizzes and programming system logs.
• Evaluated model performance in predicting on-time course submission.

Main Results:

• Found significant correlations between student learning characteristics and performance on similar programming tasks.
• The Neural Network (NN) algorithm demonstrated the highest accuracy in predicting on-time submissions.
• Different machine learning models and hyperparameters yield varying prediction efficiencies.

Conclusions:

• Machine learning is effective for predicting outcomes using educational data.
• Neural networks show strong potential for predicting student performance in online learning settings.
• Personalized learning strategies can be informed by predictive analytics.