Abstract Cloud computing has become a hot topic, and researchers have proposed various resource sharing techniques and resource provision techniques. However, few literatures pay attentions to the influence of behavior habits of user for resource provision policy. This paper proposes a behavior-based resource provision policy for cloud computing, and designs an algorithm BBTSA to analyze the user behavior data. Then, we can utilize probably theory to forecast the set of submitted task and expectation completing time of task at next time segment from the statistic results. After creating the policy table, system can dynamically adjust the resource provision policy according to the policy table and get the max VOC of unit resource. In order to evaluate the effect, we have done four-series experiments on HUTAF which is a cloud testing platform and developed by Huawei. The results indicate that the proposed resource provision policy is effective for improving the VOC and without increasing investment. The algorithm BBTSA is good for IaaS service companies to reduce investment.