Overfitting, underfitting and feature-selection biases are common issues while composing an ML algorithm. Overfitting occurs when a model learns the noise in the training data and does not ...

So, in summary, the key components of achieving good generalization (not underfitting or overfitting) in machine learning are hyper-parameter search, regularization, and out-of-sample testing.

Overfitting is a more frequent problem than underfitting and typically occurs as a result of trying to avoid overfitting.