Corpus ID: 236034095

Imitate TheWorld: A Search Engine Simulation Platform

@article{Gao2021ImitateTA,
  title={Imitate TheWorld: A Search Engine Simulation Platform},
  author={Yongqin Gao and Guangda Huzhang and Weijie Shen and Yawen Liu and Wen-Ji Zhou and Qing Da and Dan Shen and Yang Yu},
  journal={ArXiv},
  year={2021},
  volume={abs/2107.07693}
}
Recent E-commerce applications benefit from the growth of deep learning techniques. However, we notice that many works attempt to maximize business objectives by closely matching offline labels which follow the supervised learning paradigm. This results in models obtain high offline performance in terms of Area Under Curve (AUC) and Normalized Discounted Cumulative Gain (NDCG), but cannot consistently increase the revenue metrics such as purchases amount of users. Towards the issues, we build a… Expand

Figures and Tables from this paper

References

SHOWING 1-10 OF 25 REFERENCES
Generative Adversarial Nets
We propose a new framework for estimating generative models via an adversarial process, in which we simultaneously train two models: a generative model G that captures the data distribution, and aExpand
AliExpress Learning- To-Rank: Maximizing Online Model Performance without Going Online
  • 2020
Collaborative List-and-Pairwise Filtering from Implicit Feedback
The implicit feedback based collaborative filtering (CF) has attracted much attention in recent years, mainly because users implicitly express their preferences in many real-world scenarios. TheExpand
PARS: Peers-aware Recommender System
TLDR
A ranking-based choice model is applied to capture the cross-item influence and solve the resultant MaxMin problem with a decomposition algorithm to develop a peers-aware recommender system, named PARS. Expand
Are we really making much progress? A worrying analysis of recent neural recommendation approaches
TLDR
A systematic analysis of algorithmic proposals for top-n recommendation tasks that were presented at top-level research conferences in the last years sheds light on a number of potential problems in today's machine learning scholarship and calls for improved scientific practices in this area. Expand
Learning Groupwise Multivariate Scoring Functions Using Deep Neural Networks
TLDR
This work proposes a new framework for multivariate scoring functions, in which the relevance score of a document is determined jointly by multiple documents in the list, and refers to this framework as GSFs---groupwise scoring functions. Expand
RecSim: A Configurable Simulation Platform for Recommender Systems
TLDR
RecSim allows the creation of new environments that reflect particular aspects of user behavior and item structure at a level of abstraction well-suited to pushing the limits of current reinforcement learning and RS techniques in sequential interactive recommendation problems. Expand
Virtual-Taobao: Virtualizing Real-world Online Retail Environment for Reinforcement Learning
TLDR
This paper builds Virtual Taobao, a simulator learned from historical customer behavior data through the proposed GAN-SD (GAN for Simulating Distributions) and MAIL (multi-agent adversarial imitation learning) and shows that the policies trained can have significantly superior online performance to the traditional supervised approaches. Expand
Learning a Deep Listwise Context Model for Ranking Refinement
TLDR
This work proposes to use the inherent feature distributions of the top results to learn a Deep Listwise Context Model that helps to fine tune the initial ranked list and can significantly improve the state-of-the-art learning to rank methods on benchmark retrieval corpora. Expand
RecoGym: A Reinforcement Learning Environment for the problem of Product Recommendation in Online Advertising
TLDR
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. Expand
...
1
2
3
...