Abhay Shuklaabhayshukla.com·Jun 12, 2024ReLoop: A Self-Correction Continual Learning Loop for Recommender SystemsIntroduction Models deployed to production often undergo re-training to learn from new user behaviors and improve the predictions. This training loop is demonstrated in the figure below, Training data is collected from user's implicit feedback such...Discussrecsys

Abhay Shuklaabhayshukla.com·Jun 2, 2024AITM: Modeling the Sequential Dependence among Audience Multi-step Conversions with Multi-task Learning in Targeted Display AdvertisingIn this post I summarise the ideas in the paper "Modeling the Sequential Dependence among Audience Multi-step Conversions with Multi-task Learning in Targeted Display Advertising". You can find the full paper here. Recap In the previous post, we disc...DiscussEntire Space Multi-task Modelsrecsys

Abhay Shuklaabhayshukla.com·May 23, 2024ESM2: Entire Space Multi-Task Modeling via Post-Click Behavior Decomposition for Conversion Rate PredictionIn this post I summarise the ideas in the paper "Entire Space Multi-Task Modeling via Post-Click Behavior Decomposition for Conversion Rate Prediction". You can find the paper here. Recap A quick recap of the previous paper discussed in the previous ...Discuss·59 readsEntire Space Multi-task Modelsrecsys

Abhay Shuklaabhayshukla.com·May 15, 2024ESMM: Entire Space Multi-Task Model: An Effective Approach for Estimating Post-Click Conversion RateThis post is about the first paper which introduces the ESMM approach. The full paper is available here, it is fairly easy to read. Which Issues ESMM Addresses? ESMM proposes an approach to address sample selection bias (SSB) and data sparsity (DS) a...DiscussEntire Space Multi-task Modelsrecsys

Abhay Shuklaabhayshukla.com·May 6, 2024An Introduction to Entire Space Multi-Task ModelingIn this post, I will use ESMM et al. to describe ESMM and subsequent research along this line of work. I will only motivate/introduce the need for ESMM et al. in the post below. ESMM et al. aims at addressing the issues with modeling conversion (CVR)...DiscussEntire Space Multi-task Modelsrecsys

Rohit MehraforRecommender Systemsreco.hashnode.dev·Feb 9, 2024Popularity Bias in Recommender SystemsPopular items are recommended even more frequently than their popularity would warrant The long-tail phenomenon is common in RS data: in most cases, a small fraction of popular items account for most user interactions When trained on such long-tail...Discussrecsys

David Chongdavidcjw.hashnode.dev·Jun 19, 2022Why We Use Sparse Matrices for Recommender SystemsIn recommender systems, we typically work with very sparse matrices as the item universe is very large while a single user typically interacts with a very small subset of the item universe. Take YouTube for example — a user typically watches hundreds...DiscussMachine Learning