Evaluation of k-Nearest Neighbor classifier performance for direct marketing

摘要: Text data mining is a process of exploratory analysis. Classification maps into predefined groups or classes. It often referred to as supervised learning because the classes are determined before examining data. This paper describes proposed k-Nearest Neighbor classifier that performs comparative cross-validation for existing classifier. The feasibility and benefits approach demonstrated by means problem: direct marketing. Direct marketing has become an important application field mining. Comparative involves estimation accuracy either stratified k-fold equivalent repeated random subsampling. While method may have high bias; its performance (accuracy in our case) be poor due variance. Thus with was less than classifier, smaller improvement runtime larger precision recall. In we classification prediction where comparatively high.