Inproved decision tree algorithm based on grey weighted correlated degree
Xuegang Hu · Computer Engineering and Applications Journal · 2007
In the process of constructing a decision tree,the criteria of selecting partitional attributes will influence the eficiency of classification.The paper analyses the shortcoming of current algorithms for improved ID3 which are inefficient to acertain degree and subjective to measure the attributes which are important or not.Therefore,an efficient and reliable algorithm is proposed by introducing grey weighted correlated degree.The main idea of the approach algorithm is as follows:firstly through grey relational analysis,the relation model of character attributes and classification of the data mining problem is established,then using grey weighted correlated degree to modify information gain of attributes which has many values but not important.Compared with other improved ID3 by an example,the experiment has proved that the improved ID3 algorithm based on grey relational degree is efficient.