AutoTrain MLInput features
School, demographics, study behavior, support, absences, G1, and G2
Machine learning use case
Student performance prediction
Model final student grades with demographic, social, school, and earlier-grade features.
Experiment design
Setup used for the reference run
This fixed setup makes the comparison understandable and repeatable. It is an example configuration, not an automatic recommendation for every dataset.
DatasetUCI Student Performance
TargetG3 final grade
Validation80/20 holdout
Random state42
Preprocessing
One-hot encode categorical fields, scale numeric fields when needed, and evaluate models with a fixed holdout split.
Build sequence
Recreate the experiment in AutoTrain
- Inspect the dataset.Confirm field types, missing values, class balance, identifiers, and whether each feature exists at prediction time.
- Save preprocessing.Apply the documented transformations without fitting them on the holdout rows.
- Train comparable runs.Keep the dataset version and split constant while changing only the algorithm or intended hyperparameters.
- Review errors.Use task-appropriate metrics and inspect where the model fails before creating a testing tab.
Fixed reference run
Reference benchmark
These values were computed with scikit-learn using the setup above. They show what one reproducible baseline looks like; they are not copied from the cited paper and are not a production guarantee.
R² by model
Higher is betterMAE in grade points: 0.765, 0.754, and 0.778.
Reading the result
What the benchmark means
Linear Regression and Random Forest are close in this split. Earlier grades drive much of the signal, so the meaningful experiment is determined by when the prediction must be made, not only by the highest R².
Benchmark vs. your experiment: the chart above is a static reference. Results shown inside your dashboard are generated from your own dataset, parameters, validation split, and saved model.
Visual context for the student performance prediction workflow. Model selection should be based on validation metrics and product constraints.
Limitations and risk
G1 and G2 are strongly correlated with G3. Remove them when the intended decision occurs before those grades exist, and do not use predictions as the sole basis for educational decisions.
Before deployment
Repeat validation on recent, representative data; review subgroup errors; define a fallback; and monitor input and outcome drift.
Human decisions
Use the prediction as evidence, not as the sole decision maker, where an error could affect education, health, access, pricing, or customer treatment.
Journal foundation
Forecasting Students' Academic Performance in Educational Data Using Machine Learning Techniques (2026), International Journal of Information and Communication Technology Education.
The journal reference provides methodological or domain context. AutoTrain's benchmark above is a separate implementation using the stated holdout configuration.
Open journal article