"Are you sure?": Preliminary Insights from Scaling Product Comparisons to Multiple Shops
This addresses a practical problem for long-tail eCommerce shops by enabling scalable product comparisons, but it is incremental as it builds on existing recommendation concepts.
The paper tackles the challenge of scaling product comparison tables for eCommerce shops without pre-existing training data, presenting preliminary results from a pipeline tested on multiple shops, though specific numerical outcomes are not provided.
Large eCommerce players introduced comparison tables as a new type of recommendations. However, building comparisons at scale without pre-existing training/taxonomy data remains an open challenge, especially within the operational constraints of shops in the long tail. We present preliminary results from building a comparison pipeline designed to scale in a multi-shop scenario: we describe our design choices and run extensive benchmarks on multiple shops to stress-test it. Finally, we run a small user study on property selection and conclude by discussing potential improvements and highlighting the questions that remain to be addressed.