Tree Net\xAE

Tree Net\xAE is Salford's most flexible and powerful data mining tool, capable of consistently generating extremely accurate models. Tree Net has been responsible for the majority of Salford’s modeling competition awards, and its superior performance has been certified in major corporate data mining labs. Tree Net demonstrates remarkable performance for both regression and classification and can work with varying sizes of data sets, from small to huge, while readily managing a large number of columns.

The first version of Tree Net (also known as MART) was invented by Professor Jerome Friedman in 1999. The algorithm typically generates thousands of small decision trees built in a sequential error-correcting process to converge to an accurate model. Tree Net models are usually complex and thus the software generates a number of special reports designed to extract the meaning of the model, such as a ranking of the variables in order of importance and graphs illustrating the relationship between inputs and outputs.

Tree Net is undergoing active new development and will be equipped with patent-pending extensions to enhance the rapid deployment of the models and the extraction of valuable insights into data.

Technical Articles by Jerome Friedman are also available for download:

• Greedy Function Approximation: A Gradient Boosting Machine introduces the methodology.
• Stochastic Gradient Boosting discusses several improvements to the original idea.