• Corpus ID: 246035535

Learning to Rank For Push Notifications Using Pairwise Expected Regret

  title={Learning to Rank For Push Notifications Using Pairwise Expected Regret},
  author={Yuguang Yue and Yuanpu Xie and Huasen Wu and Haofeng Jia and Shaodan Zhai and Wenzhe Shi and Jonathan J. Hunt},
Listwise ranking losses have been widely studied in recommender systems. However, new paradigms of content consumption present new challenges for ranking methods. In this work we contribute an analysis of learning to rank for personalized mobile push notifications and discuss the unique challenges this presents compared to traditional ranking problems. To address these challenges, we introduce a novel ranking loss based on weighting the pairwise loss between candidates by the expected regret… 
Should I send this notification? Optimizing push notifications decision making by modeling the future
By optimizing decisions about push notifications, this work is able to send less notifications and obtain a higher open rate than the baseline system, while generating the same level of user engagement on the platform as the existing, heuristic-based, system.


RecoGym: A Reinforcement Learning Environment for the problem of Product Recommendation in Online Advertising
RecoGym is introduced, an RL environment for recommendation, which is defined by a model of user traffic patterns on e-commerce and the users response to recommendations on the publisher websites, that could open up an avenue of collaboration between the recommender systems and reinforcement learning communities and lead to better alignment between offline and online performance metrics.
Combined regression and ranking
This paper gives an efficient and effective Combined Regression and Ranking method (CRR) that optimizes regression and ranking objectives simultaneously, and shows that CRR often achieves performance equivalent to the best of both ranking-only and regression-only approaches.
Related Pins at Pinterest: The Evolution of a Real-World Recommender System
A longitudinal study of the evolution of the Pinterest recommender system and its components from prototypes to present state, showing how organic growth led to a complex system and how it managed this complexity.
Learning to rank recommendations with the k-order statistic loss
This work presents a new variant that more accurately optimizes precision at k, and a novel procedure of optimizing the mean maximum rank, which it is hypothesized is useful to more accurately cover all of the user's tastes.
Learning to Rank with Selection Bias in Personal Search
It is empirically demonstrate that learning-to-rank that accounts for query-dependent selection bias yields significant improvements in search effectiveness through online experiments with one of the world's largest personal search engines.
TF-Ranking: Scalable TensorFlow Library for Learning-to-Rank
This work introduces TensorFlow Ranking, the first open source library for solving large-scale ranking problems in a deep learning framework, which is highly configurable and provides easy-to-use APIs to support different scoring mechanisms, loss functions and evaluation metrics in the learning- to-rank setting.
Learning to rank for information retrieval
Three major approaches to learning to rank are introduced, i.e., the pointwise, pairwise, and listwise approaches, the relationship between the loss functions used in these approaches and the widely-used IR evaluation measures are analyzed, and the performance of these approaches on the LETOR benchmark datasets is evaluated.
RecSim NG: Toward Principled Uncertainty Modeling for Recommender Ecosystems
RecSim NG is described and illustrated how it can be used to create transparent, configurable, end-to-end models of a recommender ecosystem, complemented by a small set of simple use cases that demonstrate how RecSim NG can help both researchers and practitioners easily develop and train novel algorithms for recommender systems.
Ranking with ordered weighted pairwise classification
This work proposes to optimize a larger class of loss functions for ranking, based on an ordered weighted average (OWA) (Yager, 1988) of the classification losses, and shows that OWA aggregates of margin-based classification losses have good generalization properties.
Reinforcement Learning for Slate-based Recommender Systems: A Tractable Decomposition and Practical Methodology
This work develops SLATEQ, a decomposition of value-based temporal-difference and Q-learning that renders RL tractable with slates, and shows that the long-term value of a slate can be decomposed into a tractable function of its component item-wise LTVs.