Economic Denial of Sustainability (EDoS) attack is one of the major web security attacks performed on cloud hosted websites that exploits cloud’s utility model by fraudulently consuming metered resources such as network bandwidth. In such attack, the malicious traffic imitates to be legitimate and hence goes undetected. A way to defend against such attack is to analyze the browsing behavior of the users and classify them. A training dataset to be used for this classification includes some features that are fuzzy which may lead to incorrect results. Hence, there is a need of feature selection mechanism that selects only important features from the feature set and discards the irrelevant one. This paper proposes to use fuzzy entropy based feature selection for classification of website users in EDoS defense. To evaluate the performance, the classification is done with and without doing feature selection. The classification accuracy shows that the proposed approach is capable of producing more accurate results with fewer features than original feature space. © Springer Nature Singapore Pte Ltd. 2018.