Invited talk

An Optimistic-Robust Approach For Omnichannel Inventory Management


In this paper, we introduce a data-driven optimistic-robust bimodal inventory optimization (BIO) policy to allocate inventory across a retail chain to meet time-varying omnichannel demand. While prior Robust optimization (RO) methods emphasize the downside, i.e., worst-case adversarial demand, BIO also considers the upside to remain resilient like RO while also reaping the rewards of improved average-case performance. We provide structural insights about the BIO solution and how it can be tuned. Our experiments show significant benefits rethinking traditional approaches to inventory management that are siloed by channel and location, and additionally projects a 15% profitability gain for BIO over RO on real-world data from a mid-sized American retailer.