Product rotation, characterized by the constant refreshing of presented products, has been employed by traditional fast-fashion retailers to gain a competitive advantage. However, product rotation within the realm of live streaming, possessing notable practical significance owing to its high frequency, remains unexplored territory. Leveraging the minute-level product sales data from TikTok, we delve into the impact of product rotation on real-time sales. Our study unveils a novel phenomenon dubbed the “presentation threshold effect,” wherein a notable increase in sales preceding the end of the product presentation, followed by a distinct drop at the moment of product rotation. Further analyses of the underlying mechanism, by applying difference-in-discontinuity and an innovative Wasserstein Generative Adversarial Nets technique, causally reveal that the drop occurs primarily among livestream rooms with high viewer stickiness. According to bounded accumulation theory, a purchase will be made only in the range beyond a crucial tipping point in the evidence's dimensions, with the accumulation rate determined by the stimulus's strength. Therefore, sustained viewer engagement throughout the live stream, coupled with gradual evidence accumulation facilitated by streamer explanations, is crucial in triggering the threshold effect. Additionally, we find that factors such as product affinity scores, repetition of products, and timing of presentation significantly impact the magnitude of the presentation threshold effect. These results contribute to the literature on live streaming operation strategy design and underscore the importance of meticulously planning the product sequence to maximize potential sales.