Data mining is indispensable for business organizations for extracting useful information from the hugevolume of stored data which can be used in managerial decision making to survive in the competition. Dueto the day-to-day advancements in information and communication technology, these data collected from ecommerceand e-governance are mostly high dimensional. Data mining prefers small datasets than highdimensional datasets. Feature selection is an important dimensionality reduction technique. The subsetsselected in subsequent iterations by feature selection should be same or similar even in case of smallperturbations of the dataset and is called as selection stability. It is recently becomes important topic ofresearch community. The selection stability has been measured by various measures. This paper analysesthe selection of the suitable search method and stability measure for the feature selection algorithms andalso the influence of the characteristics of the dataset as the choice of the best approach is highly problemdependent.
展开▼
