For feature details, visit Whova
ABOUT THE SPEAKER:
Yifan Nie is an experienced Senior Data Scientist at Manulife, where he has been contributing to this organization’s data science department for nearly four years. He holds a PhD in Computer Science from University of Montreal, specialized in Natural Language Processing (NLP). Yifan’s domain of expertise includes a diverse range in Data Science and Machine Learning Engineering, including Time-Series Forecasting, NLP, Generative AI, Agentic AI, MLOps, and LLMOps. His extensive knowledge and innovative approach in these areas have significantly advanced data science initiatives at Manulife, helped to shape the organization’s AI future with his fellow data scientists.
TALK TITLE:
TRACK:
SUB TOPIC:
ABSTRACT:
Retrieval-augmented generation (RAG) enables generative AI models to extract accurate facts from external unstructured data sources. For structured data, RAG can be further enhanced with function (tool) calls to query databases. This paper presents an industrial case study of implementing RAG in the call center of a large financial institution. The study outlines the architecture and practical lessons learned from building a scalable RAG deployment. It also introduces enhancements for retrieving facts from structured data sources using data embeddings, achieving both low latency and high reliability. Our optimized production application demonstrates an average response time of only 7.33 seconds. Additionally, the paper compares various open‑source and closed‑source models for answer generation in an industrial environment. This paper is published in the prestigious NAACL (North American Chapter of the Association for Computational Linguistics) conference: https://aclanthology.org/2025.naacl-industry.48/
In the end, we are going to discuss how Skills based agentic application design impacts the agentic architecture for Retrieval augmented generation technique.
WHAT YOU’LL LEARN:
Unified RAG for structured + unstructured data works in production, using JSON‑chunked tables and embeddings to avoid brittle Text‑to‑SQL pipelines.
Latency dropped from 21.91s to 7.33s through targeted optimizations: lighter retrieval payloads, multi‑threading, higher‑tier vector DB, and incremental indexing.
Reliability improved with grounding rules, citations, and a confidence‑scoring LLM, reducing hallucinations and maintaining high CSR satisfaction over 26 weeks.
Model evaluations show multiple open‑source and closed‑source models perform competitively, enabling cost‑efficient deployment choices.
Operational maturity—versioning, monitoring, and feedback loops—is essential for sustaining quality in regulated enterprise environments.
Business Leaders: C-Level Executives, Project Managers, and Product Owners will get to explore best practices, methodologies, principles, and practices for achieving ROI.
Engineers, Researchers, Data Practitioners: Will get a better understanding of the challenges, solutions, and ideas being offered via breakouts & workshops on Natural Language Processing, Neural Nets, Reinforcement Learning, Generative Adversarial Networks (GANs), Evolution Strategies, AutoML, and more.
Job Seekers: Will have the opportunity to network virtually and meet over 30+ Top Al Companies.
Ignite what is an Ignite Talk?
Ignite is an innovative and fast-paced style used to deliver a concise presentation.
During an Ignite Talk, presenters discuss their research using 20 image-centric slides which automatically advance every 15 seconds.
The result is a fun and engaging five-minute presentation.
You can see all our speakers and full agenda here