Fueled by emerging short video applications (e.g., TikTok), streaming short videos is now ubiquitous among mobile users. A major problem in short video streaming is data wastage, i.e., the downloaded video data is not watched but discarded due to video switching, so the bandwidth consumed in video transferring is wasted. Our measurements show that 45.2% of video data is wasted in practice, which is a significant proportion that can lead to tremendous financial loss. To tackle the problem, this work develops a novel algorithm called Wastage Aware Streaming (WAS) which learns viewing behaviors and network conditions to reduce data wastage while keeping Quality-of-Experience (QoE) intact. Extensive evaluations show that WAS can substantially reduce data wastage, e.g., 70%, without any adverse impact on QoE, thus it offers a practical solution for data wastage in short video services.