ItemSage: Learning Product Embeddings for Shopping Recommendations at Pinterest

• URL: http://arxiv.org/abs/2205.11728v1
• Date: Tue, 24 May 2022 02:28:58 GMT
• Title: ItemSage: Learning Product Embeddings for Shopping Recommendations at Pinterest
• Authors: Paul Baltescu, Haoyu Chen, Nikil Pancha, Andrew Zhai, Jure Leskovec, Charles Rosenberg
• Abstract summary: At Pinterest, we build a single set of product embeddings called ItemSage to provide relevant recommendations in all shopping use cases. This approach has led to significant improvements in engagement and conversion metrics, while reducing both infrastructure and maintenance cost.
• Score: 60.841761065439414
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Learned embeddings for products are an important building block for web-scale e-commerce recommendation systems. At Pinterest, we build a single set of product embeddings called ItemSage to provide relevant recommendations in all shopping use cases including user, image and search based recommendations. This approach has led to significant improvements in engagement and conversion metrics, while reducing both infrastructure and maintenance cost. While most prior work focuses on building product embeddings from features coming from a single modality, we introduce a transformer-based architecture capable of aggregating information from both text and image modalities and show that it significantly outperforms single modality baselines. We also utilize multi-task learning to make ItemSage optimized for several engagement types, leading to a candidate generation system that is efficient for all of the engagement objectives of the end-to-end recommendation system. Extensive offline experiments are conducted to illustrate the effectiveness of our approach and results from online A/B experiments show substantial gains in key business metrics (up to +7% gross merchandise value/user and +11% click volume).

Related papers

• A Thorough Performance Benchmarking on Lightweight Embedding-based Recommender Systems [67.52782366565658]
  State-of-the-art recommender systems (RSs) depend on categorical features, which ecoded by embedding vectors, resulting in excessively large embedding tables. Despite the prosperity of lightweight embedding-based RSs, a wide diversity is seen in evaluation protocols. This study investigates various LERS' performance, efficiency, and cross-task transferability via a thorough benchmarking process.
  arXiv  Detail & Related papers  (2024-06-25T07:45:00Z)
• SEOpinion: Summarization and Exploration Opinion of E-Commerce Websites [0.0]
  This paper proposes a methodology coined as SEOpinion (Summa-rization and Exploration of Opinions) It provides a summary for the product aspects and spots opinion(s) regarding them, using a combination of templates' information with the customer reviews in two main phases. To test the feasibility of using Deep Learning-based BERT techniques with our approach, we have created a corpus by gathering information from the top five EC websites for laptops.
  arXiv  Detail & Related papers  (2023-12-12T15:45:58Z)
• MM-GEF: Multi-modal representation meet collaborative filtering [51.04679619309803]
  We propose a graph-based item structure enhancement method MM-GEF: Multi-Modal recommendation with Graph Early-Fusion. MM-GEF learns refined item representations by injecting structural information obtained from both multi-modal and collaborative signals.
  arXiv  Detail & Related papers  (2023-08-14T15:47:36Z)
• Towards High-Order Complementary Recommendation via Logical Reasoning Network [19.232457960085625]
  We propose a logical reasoning network, LOGIREC, to learn embeddings of products. LOGIREC is capable of capturing the asymmetric complementary relationship between products. We also propose a hybrid network that is jointly optimized for learning a more generic product representation.
  arXiv  Detail & Related papers  (2022-12-09T16:27:03Z)
• Two Is Better Than One: Dual Embeddings for Complementary Product Recommendations [2.294014185517203]
  We apply a novel approach to finding complementary items by leveraging dual embedding representations for products. Our model is effective yet simple to implement, making it a great candidate for generating complementary item recommendations at any e-commerce website.
  arXiv  Detail & Related papers  (2022-11-28T00:58:21Z)
• Entity-Graph Enhanced Cross-Modal Pretraining for Instance-level Product Retrieval [152.3504607706575]
  This research aims to conduct weakly-supervised multi-modal instance-level product retrieval for fine-grained product categories. We first contribute the Product1M datasets, and define two real practical instance-level retrieval tasks. We exploit to train a more effective cross-modal model which is adaptively capable of incorporating key concept information from the multi-modal data.
  arXiv  Detail & Related papers  (2022-06-17T15:40:45Z)
• Page-level Optimization of e-Commerce Item Recommendations [1.9590062905832923]
  We present a scalable end-to-end production system to optimize the personalized selection and ordering of item recommendation modules on the item details page. Our proposed system achieves significantly higher click-through and conversion rates compared to other existing methods.
  arXiv  Detail & Related papers  (2021-08-12T17:59:22Z)
• PreSizE: Predicting Size in E-Commerce using Transformers [76.33790223551074]
  PreSizE is a novel deep learning framework which utilizes Transformers for accurate size prediction. We demonstrate that PreSizE is capable of achieving superior prediction performance compared to previous state-of-the-art baselines. As a proof of concept, we demonstrate that size predictions made by PreSizE can be effectively integrated into an existing production recommender system.
  arXiv  Detail & Related papers  (2021-05-04T15:23:59Z)
• Personalized Embedding-based e-Commerce Recommendations at eBay [3.1236273633321416]
  We present an approach for generating personalized item recommendations in an e-commerce marketplace by learning to embed items and users in the same vector space. Data ablation is incorporated into the offline model training process to improve the robustness of the production system.
  arXiv  Detail & Related papers  (2021-02-11T17:58:51Z)
• PinnerSage: Multi-Modal User Embedding Framework for Recommendations at Pinterest [54.56236567783225]
  PinnerSage is an end-to-end recommender system that represents each user via multi-modal embeddings. We conduct several offline and online A/B experiments to show that our method significantly outperforms single embedding methods.
  arXiv  Detail & Related papers  (2020-07-07T17:13:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.