19 datasets found

A public dataset with a coupons website, suitable for evaluating the proposed methodology.

The dataset is a user-item interaction graph, with 1 billion users and tens of million items.

A conversational recommendation dataset released by Kang et al. This dataset was constructed using ParlAI to interface with Amazon Mechanical Turk (AMT) to reflect the movie...

The dataset used in the paper is a real-life dataset from education testing, recommendation systems, and finance. It contains user-item binary response data.

Ali-CCP5 is a public click-through rate prediction dataset collected from traffic logs of Taobao's RS, consisting of 85 million samples.

The dataset is a large-scale industrial dataset collected from Kuaishou, containing user interaction data with click-through as labels. The dataset has a maximum history length...

The dataset used in the paper for item cold start recommendation via Adversarial Variational Autoencoder Warm-up

The dataset used in the Controllable Gradient Item Retrieval paper, which consists of user-item interaction data and item-attribute relation data.

Yelp-2018 dataset is a real-world dataset for recommender systems, containing user-item interactions.

The associated task is to predict the movie rating on a 5-star scale. This dataset contains 6,040 users, 3,900 movies, and 1,000,209 ratings, i.e., rating matrix is 4.26% full.

The dataset used in the paper is a user-item bipartite graph, where each user and item is represented as a node, and the edges between them represent the interactions between...

The dataset used in this paper is a high-rating movie recommendation system. The objective of the system is to recommend high-rating movies to users, but the ratings for the...

The dataset is a movie review dataset with five types of nodes (movie, director, tag, writer, and user) and four types of edges (movie-director relation, movie-tag relation,...

The VideoRerank dataset is derived from Kuaishou, a widely used short-video application with a user base of over 300 million daily active users. Each sample in the dataset...

The Avito dataset is a publicly available collection of user search logs. Each sample represents a search page containing multiple ads, forming a really impressive list with...

The dataset used in the paper is a series of datasets introduced in [46], comprising large corpora of product reviews crawled from Amazon.com. Top-level product categories on...

The dataset used in the paper is Music, Book, Amazon, and Yelp. The dataset contains user-item interactions and knowledge graph information.

The dataset used in this work is a custom synthetic dataset generated using the liquid-dsp library, containing 600000 examples of each of 13.8 million examples, with SNRs...

The dataset is used for click-through rate (CTR) prediction task in recommender systems.