"Architecting AI-Driven Personalized Discovery with Generative Models"
"Architecting AI-Driven Personalized Discovery with Generative Models"
Don’t miss out and join visionaries, innovators, and thought leaders from all over the world at the Women in Tech Global Conference.
Vote by Sharing
Unite 100 000 Women in Tech to Drive Change with Purpose and Impact.
Do you want to see this session? Help increase the sharing count and the session visibility. Sessions with +10 votes will be available to career ticket holders.
Please note that it might take some time until your share & vote is reflected.
Session: Architecting AI-Driven Personalized Discovery with Generative Models
Modern search and recommendation systems must interpret ambiguous user intent and translate it into structured, actionable signals at scale. This talk explores how Generative AI and ML are used to power personalized discovery in large-scale consumer platforms. We will examine how high-level queries are decomposed into semantic tokens through LLM-driven intent modeling, normalization, and enrichment, and how these signals are integrated into retrieval, ranking, and diversification pipelines. The session covers system design considerations across token generation, feature fusion, ranking models, and dynamic content generation, along with experimentation frameworks and causal measurement strategies used to evaluate impact. Attendees will gain a systems-level understanding of how GenAI augments traditional search and recommendation architectures to drive measurable improvements in relevance, engagement, and conversion.Key Takeaways
- How LLMs turn vague user intent into structured signals for personalized search and recommendations.
- Core architecture patterns for building end-to-end AI-driven discovery systems.
- How to measure the real impact of personalization using experimentation and causal analysis.
- Practical considerations for deploying responsible, scalable AI in production.
- How to think at a systems level when applying GenAI to real-world product problems.
Bio
Banani Mohapatra:Banani Mohapatra is an AI/ML leader with 13+ years of experience across data science, product strategy, and enterprise innovation. As a Senior Data Science Leader at Walmart, she builds scalable AI systems that power personalized e-commerce experiences for millions of customers. Her work spans Generative AI, Agentic AI, causal inference, and experimentation platforms, with a focus on production-ready, responsible AI. A frequent speaker at global AI conferences, she is recognized among the top 1% of data science mentors and is an active member of the Women in Data Science (WiDS) community, committed to shaping the next generation of AI practitioners.
Manisha Arora:
Manisha Arora is a data science professional with 12+ years of experience in leading teams and driving business growth. In her current role, she leads the growth of Google Ads across Search, YouTube, and Shopping through experimentation and AI. Manisha is also passionate about democratizing data science and enabling others to level up in their careers.
