Predict Student Dropout Risk

Enter a single student's details or upload a CSV to predict dropout risk. Results are ranked by risk and can be exported for follow-up.

Learn about the projectView notebook on GitHub

Single-student form

Validate inputs and get an immediate risk prediction.

CSV batch upload

Process multiple students at once with row-level error feedback.

Ranked results

See highest-risk students first to prioritize intervention.

Export

Download predictions as CSV for sharing or analysis.

How it will work

  1. Choose: fill a form for one student or upload a CSV template.
  2. Validate inputs; fix any highlighted errors.
  3. Submit to get predictions ranked by dropout risk.
  4. Export the results as CSV for your records.

Whats going on under the hood (Not really though, I just wanted the page to have a scroll so the transition to the about page was smooth)

  param_dist = {
    'n_estimators': randint(100, 500),
    'max_depth': randint(3, 15),
    'min_samples_split': randint(2, 10),
    'min_samples_leaf': randint(1, 5)
  }


  # Create a random forest classifier
  rf = RandomForestClassifier(random_state=42, n_jobs=-1)

  # Use random search to find the best hyperparameters
  rand_search = RandomizedSearchCV(
    rf, param_distributions=param_dist,
    n_iter=10, cv=5, scoring='accuracy',
    n_jobs=-1, random_state=42