Analyzing Consumer Footprints on E-Commerce Platforms: A Multichannel Sequential Search Model with Reference Price

This study explores consumers’ footprints on a multichannel e-commerce platform to model their multichannel sequential search (MSS) behaviors. We develop a novel search model that characterizes consumers’ MSS behaviors as a threefold sequential search process consisting of cross-channel, cross-product, and cross-page searches, where consumers dynamically update their cross-channel reference prices along their search journeys. The evolving cross-channel reference price effect reshapes the attractiveness of unsearched products and channels relative to those already explored, thereby steering consumers’ future search trajectories and influencing their purchase decisions. The proposed MSS model extends the existing sequential search framework to a multichannel setting by capturing the dynamic interplay between consumers’ cross-channel search and cross-channel reference price effect. Using a large-scale data set from a leading e-commerce platform, we show that the proposed MSS model significantly outperforms the state-of-the-art sequential search models in predicting both clicks and purchases. We further demonstrate the operational value of the MSS model in optimizing the platform’s multichannel management. Our findings suggest that the MSS model supports more efficient multichannel promotion, enabling the platform to lower promotion spending while achieving a 22% improvement in profit compared with existing approaches. The platform can further enhance profitability by aligning cross-channel external links with multichannel promotion. These insights provide important managerial and operational implications for e-commerce platforms’ multichannel pricing and cross-channel management strategies.

History: Ravi Bapna, Senior Editor; Atanu Lahiri, Associate Editor.

Funding: H. Zhang is supported by the Distinguished Research Group Program (Class A) of the National Natural Science Foundation of China [Grant 72588101]. J. Liu is partially supported by the Hong Kong Research Grants Council [Grants CityU 11504322], the National Natural Science Foundation of China [Grant 72201222], and the Natural Science Foundation of Guangdong Province [Grant 2025A1515010659]. M. Wang is supported by the Key International Cooperation and Exchange Projects of the NSFC [Grant W2411062].

Supplemental Material: The online supplement is available at https://doi.org/10.1287/isre.2024.0991.