• Corpus ID: 227151183

Delayed Feedback Modeling for the Entire Space Conversion Rate Prediction

  title={Delayed Feedback Modeling for the Entire Space Conversion Rate Prediction},
  author={Yanshi Wang and Jie Zhang and Qing Da and Anxiang Zeng},
Estimating post-click conversion rate (CVR) accurately is crucial in E-commerce. However, CVR prediction usually suffers from three major challenges in practice: i) data sparsity: compared with impressions, conversion samples are often extremely scarce; ii) sample selection bias: conventional CVR models are trained with clicked impressions while making inference on the entire space of all impressions; iii) delayed feedback: many conversions can only be observed after a relatively long and… 

Figures and Tables from this paper

A Generalized Doubly Robust Learning Framework for Debiasing Post-Click Conversion Rate Prediction

A generalized learning framework is proposed that not only unifies existing DR methods, but also provides a valuable opportunity to develop a series of new debiasing techniques to accommodate different application scenarios.

MetaCVR: Conversion Rate Prediction via Meta Learning in Small-Scale Recommendation Scenarios

This work proposes a novel CVR method named MetaCVR from a perspective of meta learning to address the DDF issue in small-scale recommendation scenarios and develops an Ensemble Prediction Network (EPN) which incorporates the output of FRN and DMN to make the final CVR prediction.

Asymptotically Unbiased Estimation for Delayed Feedback Modeling via Label Correction

A new method, DElayed Feedback modeling with UnbiaSed Estimation, (DEFUSE), which aim to respectively correct the importance weights of the immediate positive, the fake negative, the real negative, and the delay positive samples at finer granularity and develops a bi-distribution modeling framework to jointly model the unbiased immediate positives and the biased delay conversions.

Generalized Delayed Feedback Model with Post-Click Information in Recommender Systems

It is shown that post-click user behaviors are also informative to conversion rate prediction and can be used to improve timeliness and establish a novel perspective that the performance gap introduced by delayed feedback can be attributed to a temporal gap and a sampling gap.

An Analysis Of Entire Space Multi-Task Models For Post-Click Conversion Prediction

An ablation approach is used to systematically study recent approaches that incorporate both multitask learning and “entire space modeling” which train the CVR on all logged examples rather than learning a conditional likelihood of conversion given clicked, and shows that several different approaches result in similar levels of positive transfer.

Towards Trustworthy AI-Empowered Real-Time Bidding for Online Advertisement Auctioning

This paper starts by analysing the key concerns of various AIRTB stakeholders and identifies three main dimensions of trust building in AIRTB, namely security, robustness and fairness, and proposes a unique taxonomy of the state of the art for each dimension.



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

This paper model CVR in a brand-new perspective by making good use of sequential pattern of user actions, i.e., impression -> click -> conversion, which is the first public dataset which contains samples with sequential dependence of click and conversion labels for CVR modeling.

An Attention-based Model for Conversion Rate Prediction with Delayed Feedback via Post-click Calibration

A novel deep learning framework is proposed to extract the pre-trained embedding from impressions/clicks to assist in conversion models and propose an inner/self-attention mechanism to capture the fine-grained personalized product purchase interests from the sequential click data.

Entire Space Multi-Task Modeling via Post-Click Behavior Decomposition for Conversion Rate Prediction

A novel deep recommendation model named Elaborated Entire Space Supervised Multi-task Model (ESM2) is devised, which employs multi-task learning to predict some decomposed sub-targets in parallel and compose them sequentially to formulate the final CVR.

A Nonparametric Delayed Feedback Model for Conversion Rate Prediction

A nonparametric delayed feedback model for CVR prediction that represents the distribution of the time delay without assuming a parametric distribution, such as an exponential or Weibull distribution is proposed.

Deep Interest Evolution Network for Click-Through Rate Prediction

This paper proposes a novel model, named Deep Interest Evolution Network~(DIEN), for CTR prediction, which significantly outperforms the state-of-the-art solutions and design interest extractor layer to capture temporal interests from history behavior sequence.

Deep Interest Network for Click-Through Rate Prediction

A novel model: Deep Interest Network (DIN) is proposed which tackles this challenge by designing a local activation unit to adaptively learn the representation of user interests from historical behaviors with respect to a certain ad.

Ups and Downs: Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filtering

This paper builds novel models for the One-Class Collaborative Filtering setting, where the goal is to estimate users' fashion-aware personalized ranking functions based on their past feedback and combines high-level visual features extracted from a deep convolutional neural network, users' past feedback, as well as evolving trends within the community.

Modeling delayed feedback in display advertising

This work introduces an additional model that captures the conversion delay and helps determining whether a user that has not converted should be treated as a negative sample -- when the elapsed time is larger than the predicted delay -- or should be discarded from the training set -- when it is too early to tell.

A Practical Framework of Conversion Rate Prediction for Online Display Advertising

This paper proposes a safe prediction framework with conversion attribution adjustment to handle over-predictions and to further alleviate over-bidding at different levels and illustrates both offline and online experimental results to demonstrate the effectiveness of the framework.

Coupled Group Lasso for Web-Scale CTR Prediction in Display Advertising

This paper proposes a novel model, called coupled group lasso (CGL), for CTR prediction in display advertising that can seamlessly integrate the conjunction information from user features and ad features for modeling and can automatically eliminate useless features for both users and ads, which may facilitate fast online prediction.