Performance Comparison of Classifiers on Reduced Phishing Website Dataset

Abstract

The Internet is becoming a necessary and important tool in everyday life. However, Internet users might have poor security for different kinds of web threats, which may lead to financial loss or clients lacking trust in online trading and banking. Phishing is described as a skill of impersonating a trusted website aiming to obtain private and secret information such as a username and password or social security and credit card number. In this paper, phising website dataset taken from UCI was investigated. Its dimension was reduced and the performance comparison of classification algorithms is studied on reduced phishing website dataset. Phishing website dataset was taken from UCI machine learning repository. This dataset consists of 11055 records and 31 features. Feature selection algorithms were applied to reduce the dimension of phishing website dataset and to obtain higher classification performance. Then, the performance of classification algorithms is compared to other data mining classification algorithms. Finally, a comparative classification performance on the reduced dataset by using the common classification algorithms is given.