In this deep exploration of employing Large Language Models (LLMs) for enhancing search recommendation systems, we will conduct a technical deep dive into the integral aspects of developing, fine-tuning, and deploying these advanced models. Our focus will be on the architecture of the models, strategies for effective data collection, and methodologies to pinpoint relevance and accuracy in recommendations.
Following this, we will examine the necessary steps to ensure the model's efficiency and stability once integrated into production environments. A significant portion of the discussion will elaborate on a practical case study using Pinterest, demonstrating how LLMs can be strategically utilized across the full marketing funnel—enhancing user activation, conversion, and retention. By the end of this presentation, attendees will gain insights not only into the technical implementation but also into deriving substantial growth and engagement by leveraging LLM technology in practical, scalable ways.
Speaker
Faye Zhang
Staff Software Engineer @Pinterest, Lead on GenAI Search Traffic Projects, Speaker, Expert in AI/ML with a Strong Background in Full-Stack Development
The speaker is a seasoned Senior Software Engineer with deep expertise in AI and Machine Learning, and a strong background in full-stack development. Intent on building the future with scalable, innovative data solutions, and significantly impact user acquisition worldwide. Notably, at Pinterest, she led its first-ever GenAI production experiment that increased traffic by 20% and user engagement by 60%. She is currently leading Pinterest AI-driven search traffic projects. Additionally, she is a well-regarded speaker, frequently contributing her insights at AI events in San Francisco and Paris.