Multi-Modality Transformer for E-Commerce: Inferring User Purchase Intention to Bridge the Query-Product Gap
This addresses the query-product mismatch problem for e-commerce platforms, representing an incremental improvement through a novel transformer-based method.
The paper tackles the problem of bridging the gap between user queries and products in e-commerce by proposing PINCER, a multi-modal transformer that transforms queries into pseudo-product representations using click-stream data and product catalogs, achieving superior performance over state-of-the-art alternatives in online retrieval experiments.
E-commerce click-stream data and product catalogs offer critical user behavior insights and product knowledge. This paper propose a multi-modal transformer termed as PINCER, that leverages the above data sources to transform initial user queries into pseudo-product representations. By tapping into these external data sources, our model can infer users' potential purchase intent from their limited queries and capture query relevant product features. We demonstrate our model's superior performance over state-of-the-art alternatives on e-commerce online retrieval in both controlled and real-world experiments. Our ablation studies confirm that the proposed transformer architecture and integrated learning strategies enable the mining of key data sources to infer purchase intent, extract product features, and enhance the transformation pipeline from queries to more accurate pseudo-product representations.