Pranjul Yadav

Senior Software Engineer - Machine Learning, Google

Conference theme:

Enhancing Digital Advertising: Domain Adaptation Techniques for Partner Cold-Start Challenges

Abstract:

Digital advertisements connects partners (sellers) to potentially interested online users. Within the digital advertisement domain, there are multiple platforms, e.g., user re-targeting and prospecting. Partners usually start with re-targeting campaigns and later employ prospecting campaigns to reach out to untapped customer base. There are two major challenges involved with prospecting. The first challenge is successful on-boarding of a new partner on the prospecting platform, referred to as partner cold-start problem. The second challenge revolves around the ability to leverage large amounts of re-targeting data for partner cold-start problem.

In this work, we study domain adaptation for the partner cold-start problem. To this end, we propose two domain adaptation techniques, SDA-DANN and SDA-Ranking. SDA-DANN and SDA-Ranking extend domain adaptation techniques for partner cold-start by incorporating sub-domain similarities (product category level information). Through rigorous experiments, we demonstrate that our method SDA-DANN outperforms baseline domain adaptation techniques on real-world dataset, obtained from a major online advertiser. Furthermore, we show that our proposed technique SDA-Ranking outperforms baseline methods for low CTR partners.

Speaker biography:

Pranjul Yadav completed his B.S. from Indian Institute of Technology and Ph.D. from University of Minnesota with a focus on Machine Learning. Post Ph.D. Pranjul worked at Criteo Research (2017-2020) on transfer learning and currently at Google (Senior Engineer - Machine Learning). Pranjul's interest lies in Data Mining, Machine Learning and its applications in E-commerce and Healthcare. Pranjul has extensively published at leading conferences such as SDM, IEEE' BIGDATA, ICDM, RECSYS, AMIA, ICMLA, ICHI, CIKM and journals such as ACM Computing surveys, and at Critical Care Medicine.

Organized by:

Logo Escuela Politécnica Nacional
Logo Facultad de Ingeniería de Sistemas

Partners:

Logo Universidad Catolica de Cuenca
Logo UDLA
Logo Universidad de Puerto Rico
Logo Universidade Federal do Ceará
Logo Universidad de Cuenca
Logo Universidad YACHAY
Universidad Técnica Particular de Loja
Fundación Openlab Ecuador

Publisher:

logo de IEEE CPS