MLDS speaker · 2026

Satyen Abrol

Vice President - Machine LearningGlance

About Satyen Abrol

Dr. Satyen Abrol is a seasoned leader in machine learning, personalization, and recommender systems, currently heading the Personalization and Recommendation teams at Glance as Vice President of Machine Learning, where he drives innovation in user-centric AI and large-scale recommendation platforms. Before joining Glance, Satyen served as Director of Research (Data Science) at Rakuten, leading cross-geographical teams on customer understanding, marketing science, social graph research, fraud prevention, and recommendation systems that span ecommerce, mobile, and fintech applications. His work at Rakuten included building scalable customer social graph embeddings and audience science frameworks that enhanced user engagement and business outcomes. Earlier in his career, Satyen held key technical roles at Samsung Electronics, where he developed large-scale machine learning models and production pipelines to infer smartphone user demographics and interests from behavioral and app usage data, powering personalized experiences across Samsung’s ecosystem. He also worked at VMware (California), contributing to performance data analysis, pattern recognition modules, and scalable system design. Satyen holds a PhD in Computer Science from the University of Texas at Dallas, where his dissertation focused on “Location Mining in Online Social Networks”, advancing methodologies in graph-based data mining and semi-supervised learning. He is an active researcher and innovator with 15+ publications in peer-reviewed conferences and journals, 20+ patents in areas spanning recommendation systems, user profiling, and machine learning, and is co-author of the book Analyzing and Securing Social Networks—a comprehensive exploration of social media analytics and privacy frameworks. Satyen’s expertise spans AI/ML research, scalable systems, user modeling, and data-driven personalization, making him a sought-after speaker and mentor in both industry and academic forums.

1 edition on the MLDS stage · 1 session on record

Satyen Abrol, Vice President - Machine Learning, Glance

Talks at MLDS

Sessions from the MLDS agendas, newest first.

  1. MLDS 2026

    Bengaluru
    26–27 Mar 2026

    • Mar 27, 2026 · 15:50–16:10 · Hall 3 · Bengaluru

      Tech Talks

      Solving the Cold-Start Problem in Fashion Recommendations Using LLMs

      The talk focuses on one of the hardest problems in fashion recommendation systems—new users and new items in rapidly changing catalogs—and how recent advances in large language models enable fundamentally different approaches to representation, understanding, and bootstrapping recommendations at scale. The session will share practical system designs, trade-offs, and lessons learned from using LLMs to address cold start across candidate generation and ranking, including how we combine textual, visual, and contextual signals to reduce dependence on historical interaction data. The emphasis will be on what translated to measurable online impact, and where LLM-based approaches helped—or failed—compared to traditional heuristics and embedding-based methods. I believe this talk would resonate well with ML practitioners, recommender system engineers, and applied researchers, and would complement the conference’s focus on recommender systems, applied machine learning, and real-world deployments.

    MLDS 2026 agenda MLDS 2026 talk recordings on YouTube (opens in a new tab)

MLDS 2027Feb 25–26 / Mar 4–5Early bird till 15 Dec

Get passes