Evaluation, Investigation and Comparison of Different Data Mining Methods in Processing Database

Database processing is very important in exploiting memory consumption, compression is one of the essential pre-processing tools to reduce the memory needed to store and load data for processing, the compression method presented in this the article was tested by using the suggested examples to show the effect of repetition in the database as well as the size of the database, and the results indicated that whenever the repetition is increased, the density will increase. Condensation is one of the important activities for data pre-processing before data mining. Data mining methods such as Naïve Bayes, Nearest neighbor and decision tree are tested. The implementation of three methods showed that the Naïve Bayes method is effectively used when data symbols are classified and that method can be successfully used in machine learning. The Nearest neighbor method is very suitable when the data symbols are constant or categorized. Decision tree is the third method that was tested and this method is a simple predictive method that was implemented through the use of simple rule methods in data classification. The success of data mining implementation depends on the completeness of the database, which is shown through the data repositories, which should be organized by using the important characteristics of the data repositories .

کلیدواژه ها:

Data Mining ، Preprocessing ، Decision Tree