MerRec: A Large-scale Multipurpose Mercari Dataset for Consumer-to-Consumer Recommendation Systems (2024-02-22T00:00:00.000000Z)

TL;DR

This dataset, extensively evaluated across three recommendation tasks, establishes a new benchmark for the development of advanced recommendation algorithms in real-world scenarios, bridging the gap between academia and industry and propelling the study of C2C recommendations.

Abstract

In the evolving e-commerce field, recommendation systems crucially shape user experience and engagement. The rise of Consumer-to-Consumer (C2C) recommendation systems, noted for their flexibility and ease of access for customer vendors, marks a significant trend. However, the academic focus remains largely on Business-to-Consumer (B2C) models, leaving a gap filled by the limited C2C recommendation datasets that lack in item attributes, user diversity, and scale. The intricacy of C2C recommendation systems is further accentuated by the dual roles users assume as both sellers and buyers, introducing a spectrum of less uniform and varied inputs. Addressing this, we introduce MerRec, the first large-scale dataset specifically for C2C recommendations, sourced from the Mercari e-commerce platform, covering millions of users and products over 6 months in 2023. MerRec not only includes standard features such as user_id, item_id, and session_id, but also unique elements like timestamped action types, product taxonomy, and textual product attributes, offering a comprehensive dataset for research. This dataset, extensively evaluated across three recommendation tasks, establishes a new benchmark for the development of advanced recommendation algorithms in real-world scenarios, bridging the gap between academia and industry and propelling the study of C2C recommendations. Experiment code (https://github.com/mercari/mercari-ml-merrec-pub-us) and dataset (https://huggingface.co/datasets/mercari-us/merrec) are released.

Authors

Zhen Tan

2 papers

Tianlong Chen

3 papers

Lichi Li

1 papers

TL;DR

Abstract

Authors

References88 items

Bridging Language and Items for Retrieval and Recommendation

From Data to Human-Readable Requirements: Advancing Requirements Elicitation through Language-Transformer-Enhanced Opportunity Mining

STEM: Unleashing the Power of Embeddings for Multi-task Recommendation

Temporal Interest Network for User Response Prediction

Deep Context Interest Network for Click-Through Rate Prediction

Sustainable Business Models of E-marketplaces: An Analysis from the Consumer Perspective

Amazon-M2: A Multilingual Multi-locale Shopping Session Dataset for Recommendation and Text Generation

ESMC: Entire Space Multi-Task Model for Post-Click Conversion Rate via Parameter Constraint

TransAct: Transformer-based Realtime User Action Model for Recommendation at Pinterest

EulerNet: Adaptive Feature Interaction Learning via Euler's Formula for CTR Prediction

FinalMLP: An Enhanced Two-Stream MLP Model for CTR Prediction

PEPNet: Parameter and Embedding Personalized Network for Infusing with Personalized Prior Information

Tenrec: A Large-scale Multipurpose Benchmark Dataset for Recommender Systems

FiBiNet++: Reducing Model Size by Low Rank Feature Interaction Layer for CTR Prediction

KuaiRand: An Unbiased Sequential Recommendation Dataset with Randomly Exposed Videos

Sampling Is All You Need on Modeling Long-Term User Behaviors for CTR Prediction

Will You Accept the AI Recommendation? Predicting Human Behavior in AI-Assisted Decision Making

Graph Trend Filtering Networks for Recommendation

Denoising User-aware Memory Network for Recommendation

Modeling the Sequential Dependence among Audience Multi-step Conversions with Multi-task Learning in Targeted Display Advertising

A User-Adaptive Layer Selection Framework for Very Deep Sequential Recommender Models

Learning Transferable Visual Models From Natural Language Supervision

FM2: Field-matrixed Factorization Machines for Recommender Systems

Personalized Embedding-based e-Commerce Recommendations at eBay

RecBole: Towards a Unified, Comprehensive and Efficient Framework for Recommendation Algorithms

Netflix

Progressive Layered Extraction (PLE): A Novel Multi-Task Learning (MTL) Model for Personalized Recommendations

Open Benchmarking for Click-Through Rate Prediction

DCN V2: Improved Deep & Cross Network and Practical Lessons for Web-scale Learning to Rank Systems

Deep Feedback Network for Recommendation

Mixed Negative Sampling for Learning Two-tower Neural Networks in Recommendations

Interpretable Click-Through Rate Prediction through Hierarchical Attention

Learning Feature Interactions with Lorentzian Factorization Machine

Sampling-bias-corrected neural modeling for large corpus item recommendations

A pareto-efficient algorithm for multiple objective optimization in e-commerce recommendation

Adaptive Factorization Network: Learning Adaptive-Order Feature Interactions

Deep Learning Recommendation Model for Personalization and Recommendation Systems

Modeling Heart Rate and Activity Data for Personalized Fitness Recommendation

POG: Personalized Outfit Generation for Fashion Recommendation at Alibaba iFashion

BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer

Scalability and sparsity issues in recommender datasets: a survey

Deep Interest Evolution Network for Click-Through Rate Prediction

A Simple Convolutional Generative Network for Next Item Recommendation

Modeling Task Relationships in Multi-task Learning with Multi-gate Mixture-of-Experts

Entire Space Multi-Task Model: An Effective Approach for Estimating Post-Click Conversion Rate

xDeepFM: Combining Explicit and Implicit Feature Interactions for Recommender Systems

BlockDrop: Dynamic Inference Paths in Residual Networks

ATRank: An Attention-Based User Behavior Modeling Framework for Recommendation

Deep & Cross Network for Ad Click Predictions

Neural Factorization Machines for Sparse Predictive Analytics

Attentional Factorization Machines: Learning the Weight of Feature Interactions via Attention Networks

Deep Learning Based Recommender System

Deep Interest Network for Click-Through Rate Prediction

DeepFM: A Factorization-Machine based Neural Network for CTR Prediction

Improved Deep Metric Learning with Multi-class N-pair Loss Objective

Self-Critical Sequence Training for Image Captioning

Deep Neural Networks for YouTube Recommendations

Wide & Deep Learning for Recommender Systems

The MovieLens Datasets: History and Context

Session-based Recommendations with Recurrent Neural Networks

Neural Machine Translation of Rare Words with Subword Units

Online Recommendation Systems in a B2C E-Commerce Context: A Review and Future Directions

Survey on Collaborative Filtering, Content-based Filtering and Hybrid Recommendation System

Adam: A Method for Stochastic Optimization

Deep Learning of Representations: Looking Forward

Collaborative filtering recommender systems

Factorization Machines

A Dynamic Trust Evaluation Model on C2C Marketplaces

An efficient algorithm for web recommendation systems

Understanding the Emerging C2C Electronic Market in China: An Experience-Seeking Social Marketplace

Improving recommendation lists through topic diversification

Hybrid Recommender Systems: Survey and Experiments

Adaptive Mixtures of Local Experts

How Green Consumption Values Affect the Intention-Behavior Relationship in C2C e-commerce

An empirical investigation of determinants for adoption of C2C auction marketplaces

An empirical investigation of determinants for adoption of C2C auction marketplaces