A company is developing an ML model to predict customer churn. The model performs well on the training dataset but does not accurately predict churn for new data. Which solution will resolve this…

Decreasing the regularization parameter would reduce the penalty on model complexity, potentially exacerbating the overfitting problem.

Overfitting occurs when a model learns the training data too well, including its noise, leading to poor generalization on unseen data. Increasing the regularization parameter penalizes large coefficients, thereby simplifying the model and reducing its ability to overfit the training data.

Adding more features to the input data might increase model complexity and potentially worsen overfitting if not carefully selected or if the model is already overfitting.

Training the model for more epochs would further expose it to the training data, likely leading to increased overfitting rather than resolving it.