Abstract:

Operational data is gradually increasing with the effect of technological developments. Due to the increase in the amount and diversity of data, many difficulties are faced in data analysis and the evaluation of its results. Since the data transferred to the analysis stage consists of both relevant and irrelevant variables, time and resources required for analysis increases. It is obvious that resources and time are always limited. The aim of this study is to increase the success of classification methods under the limitation of time and resources by applying various feature selection methods. Feature selection methods were used on a set of banking customer data in order to determine the appropriate subsets for classification. Then, a classification method was applied on these selected subsets of features. By comparing the classification results, the contribution of the feature selection methods to the classification success was measured.

Keywords: