arXiv Machine Learning By Prasenjit Dey, Frank McIntyre, Arnab Sinha

Sequential Multimodal Evidence Optimization for Product Media Ranking in E-Commerce

Read the original on arXiv Machine Learning →

arXiv:2608. 15662v1 Announce Type: new Abstract: On modern e-commerce stores, customers consume ordered slates of heterogeneous product media, such as images, videos, and 3D renders, before making purchase decisions.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Machine Learning
Aug 27

DCEO: Direct Causal Effect Optimization for Long-Term User Value Modeling in E-commerce Search

The paper introduces DCEO, a data‑driven framework that learns item‑level proxy scores directly aligned with long‑term user objectives in e‑commerce search. It aggregates these scores into a user‑level metric, measures alignment via relative causal effect, and uses an actor‑critic model to generate context‑dependent fusion weights for multiple objectives. Offline experiments and a 41‑day online A/B test show DCEO improves GMV by 0.36% over traditional proxies.

By Junzhao Zhang, Tao Zhang, Liren Yu, Feiyi Dong, Zhixuan Zhang, Dan Ou, Haihong Tang
arXiv Computer Vision
Sep 18

Grounded Product Understanding in Livestream Videos

The paper introduces GPUB, a large-scale benchmark for grounded product understanding in e‑commerce livestream videos, featuring 3,000 livestreams, 31K fashion products, and multi‑moment temporal annotations. It defines three evaluation tasks, with the main task (GPrU) requiring simultaneous product identification and moment localization. Existing multimodal models perform poorly on GPrU, prompting the authors to develop UniPro, which improves performance by learning product‑aligned, temporally structured representations.

By Xinyu Zhang, Junjie Chen, Jiawei Ge, Qianlong Li, Libin Ma, Baokun Pan, Yahui Luo