Classifying Streaming Data
This chapter is concerned with the classification of streaming data, i.e. data which arrives (generally in large quantities) from some automatic process over a period of days, months, years or potentially forever.
Generating a classification tree for streaming data requires a different approach from the TDIDT algorithm described earlier in this book. The algorithm given here, H-Tree, is a variant of the popular VFDT algorithm which generates a type of decision tree called a Hoeffding Tree. The algorithm is described and explained in detailed with accompanying pseudocode for the benefit of readers who may be interested in developing their own implementations. An example is given to illustrate a way of comparing the rules generated by H-Tree with those from TDIDT.
KeywordsEntropy Val12 Sorting