Algorithm 1: Logistic Regression algorithm pseudocode

Input:

- Training data: X_train, y_train

- Testing data: X_test

- Learning rate: η

- Regularization parameter: λ

- Number of iterations: num_iterations

Output: Predicted macrosomia risk for each test

Initialize weights w to zeros

For each iteration i in 1 to num_iterations:

Compute sigmoid function on X_train * w to obtain z

Compute gradient of loss function with respect to weights w

Update weights w using gradient descent

Compute sigmoid function on X_test * w to obtain predicted risk y_pred

Return predicted macrosomia risk for each test example: y_pred