User Modeling and Personalization

Personalization is the science of developing user models to anticipate the interaction each user will have with a product. We look for ways in which personalization can be used within real-time experiences on mobile devices with rich context. Key problems in this area include contextual profiling, context-based intent prediction, personalized recommendations, and real-time federated search.

Publications

Paper
|
August 24, 2022
CIKM 2022

Improving Text-Based Similar Product Recommendation for Dynamic Product Advertising at Yahoo

Paper
|
November 15, 2021
IEEE Big Data 2021 (Poster)

BAN:Large Scale Brand ANonymization for Creative Recommendation Via Label Light Adaptation

Paper
|
October 27, 2021
IEEE Big Data 2021

Dynamic Length Factorization Machinesfor CTR Prediction

Paper
|
October 27, 2021
IEEE Big Data 2021

Mitigating Divergence of Latent Factors via Dual Ascent for Low Latency Event Prediction Models

Paper
|
January 15, 2021
WWW 2021

FM^2: Field-Matrixed Factorization Machines for Recommender Systems

Paper
|
July 24, 2020
CIKM 2020

Prospective Modeling of Users for Online Display Advertising via Deep Time-Aware Model

Paper
|
May 15, 2020
KDD 2020

Time-Aware User Embeddings as a Service

Paper
|
May 1, 2020
UMAP 2020

Cohort Modeling Based App Usage Prediction

Paper
|
January 1, 2019
AdKDD

Time-Aware Prospective Modeling of Users for Online Display Advertising

Paper
|
January 1, 2019
AdKDD

Learning from Multi-User Activity Trails for B2B Ad Targeting

Paper
|
January 1, 2019
ICMLA 2019

Large-Scale Gender/Age Prediction of Tumblr Users

Paper
|
January 1, 2019
KDD

Understanding Consumer Journey Using Attention-Based Recurrent Neural Networks

Paper
|
January 1, 2019
Scientific Report

Community Detection on Networks with Ricci Flow