In BigML we use the term model to refer to a single decision tree-like model when we cite it in particular, and a predictive model when we refer to it in general.
The term model used in particular refers to a proprietary Decision Tree Model based on the Classification and Regression Trees (CART) algorithm proposed by Leo Breiman. This supervised Learning algorithm predicts the value of a field in your dataset, called the objective field. A BigML model is one of the predictive models available in the BigML platform, and it is recommended as the first choice to practice because it can be used to solve both classification and regression problems, it is robust to noise, and its results can be easily interpreted.
To build a model, you need to start from a dataset. The model will extract the existing patterns or rules found in your dataset and, using these rules, your model will predict the value of the objective field for new instances where this value is unknown.
To learn more about models, please:
- Watch this video for a gentle introduction to models. This demo showcases what is a model, how to create it, and interpret the results.
- Read the chapter 1 of BigML's Dashboard documentation about models, or check the models API documentation for more details on the arguments and properties of a model.
- Check these related questions to continue learning about other predictive models: Which models does BigML work with?, What is an ensemble?, What is a Prediction?, What are some of the popular algorithms for Machine Learning?