On changing continuous attributes into ordered discrete attributes

摘要: The large real-world datasets now commonly tackled by machine learning algorithms are often described in terms of attributes whose values real numbers on some continuous interval, rather than being taken from a small number discrete values. Many able to handle attributes, but requires far more CPU time for corresponding task with attributes. This paper describes how can be converted economically into ordered before given the system. Experimental results wide variety domains suggest this change representation does not result significant loss accuracy (in fact it sometimes significantly improves accuracy), offers reductions time, typically factor 10