Item$3$

Item $3$

Training, Validation and Testing Data

Building an algorithm, assessing its performance, and evaluating the final selected algorithm usually occurs by using multiple datasets. There are a few common datasets used throughout this process.

The goal of this activity is to demonstrate your understanding between training, validation, testing, and new data.

Match each term to its correct description.

Testing

Training

Validation

New data

Match each of the options above to the items below.

the data used to build the algorithm and $$learn$$ the relationship between the predictors and the target variable

the data used to assess how well the model estimates the target variable to make a recommendation

the data used to evaluate the final selected algorithm and see how well it performs

the data used to apply the final selected model to perform prediction or classification