What could be an effect of overfitting a predictive model?

When a predictive model is overfitted, it becomes excessively complex and starts to capture not just the underlying data patterns but also the random noise present in the training dataset. This means that while the model may show high accuracy when evaluated against the training data, it often lacks generalization capabilities when applied to new, unseen data.

Capturing noise instead of the true signal leads to a model that may have a very low error rate on the training set but performs poorly on unseen data, as it has essentially learned to fit the peculiarities and variations of the training set rather than the underlying distribution of the entire population. Therefore, option C accurately describes one of the key consequences of overfitting in predictive modeling.