The best way to reduce overfitting is with cross-validation. The general way is to set up a hold-out sample (or do n-fold cv if you don't have a lot of data) and then use this cross-validation hold-out sample to do feature, parameter, and model selection. With this technique however there is a risk of overfitting to your hold-out sample, so you want to use your domain expertise to consider what features and models to use, especially if you don't have a lot of data.

Overfitting is somewhat of an overloaded term. People often use it to describe the related process of creating models after you have looked at past results (e.g. models which can correctly "predict" the outcomes of all past presidential elections), and also in a more technical sense of fitting a parabola to 3 points. These are technically related, but I think it would be clearer to have two distinct terms for them.