Predicting student performance using data from an auto-grading system
Bibliographic record
Abstract
As online auto-grading systems appear, information obtained from those systems can potentially enable researchers to create predictive models to predict student behaviour and performances. In the University of Waterloo, the ECE 150 (Fundamentals of Programming) Instructional Team wants to get an insight into how to allocate the limited teaching resources better to achieve improved educational outcomes. Currently, the Instructional Team allocates tutoring time in a reactive basis. They help students "as-requested". This approach serves those students with the wherewithal to request help; however, many of the students who are struggling do not reach out for assistance. Therefore, we, as the Research Team, want to explore if we can determine students which need help by looking into the data from our auto-grading system, Marmoset. In this paper, we conducted experiments building decision-tree and linear-regression models with various features extracted from the Marmoset auto-grading system, including passing rate, testcase outcomes, number of submissions and submission time intervals (the time interval between the student's first reasonable submission and the deadline). For each feature, we interpreted the result at the confusion matrix level. Specifically for poor-performance students, we show that the linear-regression model using submission time intervals performs the best among all models in terms of Precision and F-Measure. We also show that for students who are misclassified into poor-performance students, they have the lowest actual grades in the linear-regression model among all models. In addition, we show that for the midterm, the submission time interval of the last assignment before the midterm predicts the midterm performance the most. However, for the final exam, the midterm performance contributes the most on the final exam performance.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.014 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".