We consider a multi-retailer system where the sellers are connected with each other via a transportation network and the transactions with the consumers happen on a platform. Each consumer is serviced by only one retailer. Since the demands to the sellers (i.e., the retailers on the platform) are stochastic in nature, supplies can be either in excess or in deficit. Transshipping these items laterally among the retailers benefits both, the platform and the retailers. For retailers, excess supply leads to wastage and deficit to a loss of revenue, while via transshipment, they get a better outcome. The platform can also earn some revenue in facilitating this process. However, only the sellers know their excess (which can be salvaged at a price or transshipped to another seller) or the deficit (which can be directly procured from a supplier or transshipped from another seller), both of which have multiple information that is private. We propose a model that allows lateral transshipment at a price and design mechanisms such that the sellers are incentivized to voluntarily participate and be truthful. Experimenting on different types of network topologies, we find that the sellers at more central locations in the network get an unfair advantage in the classical mechanism that aims for economic efficiency. We, therefore, propose a modified mechanism with tunable parameters which can ensure that the mechanism is more equitable for non-central retailers. Our synthetic data experiments show that such mechanisms do not compromise too much on efficiency, and also reduce budget imbalance.

Trend driven retail industries such as fashion, launch substantial new products every season. In such a scenario, an accurate demand forecast for these newly launched products is vital for efficient downstream supply chain planning like assortment planning and stock allocation. While classical time-series forecasting algorithms can be used for existing products to forecast the sales, new products do not have any historical time-series data to base the forecast on. In this paper, we propose and empirically evaluate several novel attention-based multi-modal encoder-decoder models to forecast the sales for a new product purely based on product images, any available product attributes and also external factors like holidays, events, weather, and discount. We experimentally validate our approaches on a large fashion dataset and report the improvements in achieved accuracy and enhanced model interpretability as compared to existing k-nearest neighbor based baseline approaches.