Below is for novices like me Out-of-sample validationOut of sample testing refers tousing “new” data which is not found in the dataset used to build the model. This is often considered the best method for testing how good the model is for predicting results on unseen new data: its “predictive performance”.
In statistical modeling, the term “in-sample” refers to data that is used to fit or train a model. On the other hand, “out-of-sample” data refers to data that is held back from the model training process and used to evaluate the performance of the model.
