The commercial successor to C4.5. The software can be easily obtained from the website as a demo version which is limited by the fact that it cannot process more than 400 training or test instances. With a very clean, usable interface, See5 is extremely easy to use for the newcomer to the field but is sufficiently powerful for the expert to obtain excellent results with. The tool allows a range of data samples and can be loaded with user-specified data from a file of comma separated values. Test data, misclassfication costs and a range of options can be specified before a decision tree is constructed. These include pruning, winnowing, boosting and the ability to set fuzzy thresholds. The decision tree is generated as an ASCII representation with mis-classification rates. The tree can then be examined using new (user-defined) instances for it’s prediction accuracy and can also be cross-examined with instances from the training or test sets. Output can also be converted to a set of rules.

This entry was posted in software. Bookmark the permalink.

Leave a Reply

Your email address will not be published. Required fields are marked *

* Copy This Password *

* Type Or Paste Password Here *

You may use these HTML tags and attributes: <a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <strike> <strong>