Practical Applications of Data Mining

3.7 exerCises 129

3.6 CHAPTER SUMMARY

In this chapter, several algorithms for classification methods in data mining were

presented. A general introduction to classification and its role in data-mining

applications was also given. Every approach to classification learning has its

advantages and disadvantages. The beauty of the “separate and conquer” strat-

egy is its simplicity, while the advantage of the “divide and conquer” approach

is its accuracy. The partial decision-tree approach combines the benefits of both

methods.

The Prism, Induct, REP, IREP, and RIPPER algorithms, have been used to

elaborate the separate-and-conquer approach. As for the divide-and-conquer

approach, methods such as ID3, C4.5, and C5.0 have been used to illustrate ...