Encoding consumer interests into product snippets with a multi-criteria genetic optimization approach

Abstract

As an essential product cue in consumer information foraging, textual snippets can convey valuable scents that attract consumers to further access products, paving the way for online sellers to seize a competitive advantage. Premised on shopping goals theory, this study proposes a novel approach to designing high-quality product snippets that are particularly enhanced with consumer interests. First, snippet encoding is formulated as a multi-criteria optimization problem in which information sources are incorporated to distill consumer-appealing keywords considering both driving search and attracting selection, as well as to integrate the perspectives of sellers and consumers. Subsequently, a constrained genetic solution algorithm is developed, which copes well with the evolutionary nature of the problem to optimize snippets in an effective and efficient manner. Extensive experiments are conducted to verify the validity and superiority of the proposed approach.