[Adapt] [Seminar] Asymptotically Unbiased Estimation for Delayed Feedback Modeling via Label Correction

[朱煜烨]

Hi Adapters,

In this seminar, I'd like to introduce a problem of crucial importance for the conversion rate (CVR) prediction: Delayed Feedback. In my talk, I will mainly talk about a WWW-2022 paper named "Asymptotically Unbiased Estimation for Delayed Feedback Modeling via Label Correction", along with the following works:

1. Real Negatives Matter: Continuous Training with Real Negatives for Delayed Feedback Modeling (DEFER)

2. Capturing Delayed Feedback in Conversion Rate Prediction via Elapsed-Time Sampling (ESDFM)

3. Addressing Delayed Feedback for Continuous Training with Neural Networks in CTR prediction (FNW)

Time: 2022/09/14 16:00-18:00

Venue: 
Tencent meeting link: https://meeting.tencent.com/dm/bW0BdEsGAmHl
Meet Number：233-726-220

Hope you will enjoy my talk,
Yuye Zhu