-
Company dataset
The company dataset contains about 700 million instances and its CTR is about 0.08. -
Criteo dataset
The Criteo dataset contains 39 features about which 13 of them are integer features and 26 of them are categorical and some features can have missing values. -
Avazu dataset
The Avazu dataset contains 23 features about the user and the device that is used to connect to the website. The features include the hour, website domain and category, device... -
Taobao Dataset
Precise user modeling is critical for online personalized recommen-der services. Generally, users’ interests are diverse and are not limited to a single aspect, which is... -
Amazon Book Dataset
Amazon book data set contains book reviews and metadata from Amazon. Following previous work, we regard reviews as positive samples and randomly select products not rated by a... -
Alibaba Display Advertising Platform Dataset
The production data set collected from Alibaba display advertising platform. We randomly select about 1% of 1-day samples for training and 0.1% of the next-day samples for... -
End-to-End User Behavior Retrieval in Click-Through Rate Prediction Model
Click-Through Rate (CTR) prediction is one of the core tasks in recommender systems (RS). It predicts a personalized click probability for each user-item pair.
