CART is a decision tree tool that automatically sifts large, complex databases, searching for and isolating significant patterns and relationships. This discovered knowledge is then used to generate predictive models. In addition, it is a pre-processing complement to other data analysis techniques. For example, outputs can be used as inputs to improve the predictive accuracy of neural nets and logistic regression. Other features include the ability to automatically detect distinct discrete variables classes, native support for text datasets, and support for variable names up to 32 characters.