Context‐based dynamic pricing with online clustering

We consider a context-based dynamic pricing problem of online products, which have low sales. Sales data from Alibaba, major global retailer, illustrate the prevalence low-sale products. For these existing single-product algorithms do not work well due to insufficient samples. To address this challenge, we propose policies that concurrently perform clustering over product demand and set individual decisions on fly. By identifying products similar patterns, utilize sales within same cluster improve estimation for better decisions. evaluate using regret, result shows when functions come multiple clusters, our significantly outperform traditional policies. Numerical experiments real dataset Alibaba demonstrate proposed policies, compared with several benchmark increase revenue. The results show is an effective approach tackling problems associated