A Practical Price Optimization Approach for Omni-channel Retailing

Consumers are increasingly navigating across sales channels to make purchases. The common retail practice of pricing channels independently is unable to achieve the desired profitable coordination required between channels. As part of a joint partnership agreement with IBM Commerce, we engaged with three major retailers over two years, and developed advanced omni-channel pricing (OCP) solutions that are used by several retail chains today. A big-data platform is employed to develop an omni-channel framework to model location-specific cross-channel demand interactions. An integrated OCP optimization formulation profitably coordinates prices for non-perishable products across channels and store locations, taking into account the impact of competition, and sales goals. The resultant non-linear model is non-convex and NP-hard, and practically efficient optimization approaches are prescribed, along with computational results using real- world data. In the absence of certain side constraints, we derive insightful results on price coordination across channels. An OCP implementation for a large retail chain yielded a 7% profit lift. IBM Commerce deployed proprietary versions of these models into production in 2014. Subsequently, IBM attributed the opening of several new market opportunities as well as significant incremental revenue to the deployed solution. In 2015, IBM formally recognized this work as a significant research accomplishment.


IBM T. J. Watson Research Center, December 2015