# Prediction of Success or Failure for Final Examination using Nearest Neighbor Method to the Trend of Weekly Online Testing

## TL;DR

This paper presents a method using nearest neighbor analysis of online testing ability trends to predict students' success or failure in final exams early in the course.

## Contribution

It introduces a novel application of the nearest neighbor method to ability trend data for early prediction of exam outcomes, improving accuracy.

## Key findings

- The method achieves higher prediction accuracy than previous approaches.
- ROC and recall-precision curves effectively evaluate the prediction performance.
- Using ability trend data enhances early intervention strategies.

## Abstract

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.