Prediction of Success or Failure for Final Examination using Nearest Neighbor Method to the Trend of Weekly Online Testing
This work addresses early intervention for students at risk of failing exams in educational settings, though it is incremental as it builds on existing learning analytics with a new method.
The paper tackled predicting student success or failure in final exams by analyzing trends in estimated abilities from weekly online tests, using a novel nearest neighbor method to measure learning skill similarity, which improved prediction accuracy.
Using the trends of estimated abilities in terms of item response theory for online testing, we can predict the success/failure status for the final examination to each student at early stages in courses. In prediction, we applied the newly developed nearest neighbor method for determining the similarity of learning skill in the trends of estimated abilities, resulting a better prediction accuracy for success or failure. This paper shows that the use of the learning analytics incorporating the trends for abilities is effective. ROC curve and recall precision curve are informative to assist the proposed method.