LH-151
Sessions in LH-151
AI in Risk and Antifraud Domain
Discover how Transformer-based AI models are revolutionizing fraud prevention by extracting hidden patterns from payment histories. Madhumitha will reveal how these advanced models move beyond static rules to deliver real-time, intelligent fraud detection that reduces chargebacks and boosts revenue. Learn practical strategies for deploying state-of-the-art NLP architectures in payment workflows and turning your transaction data into a competitive advantage against evolving fraud tactics.
“Millions-to-One, Words-to-Terms” - Generative AI in Action for Rare Disease Diagnosis and Clinical Data Harmonization
We present two Generative AI (GenAI)-based frameworks and practices that address 2 precision medicine data challenges. "millions-to-one" challenge in genomics: filtering millions of variants from a patient down to a single causative variant with diagnosis report. "words-to-terms" challenge: transforming unstructured, jargon-laden clinical data into standardized, terms encoded in ontologies.
Building an End-to-end ML Platform
Understand the components of an end-to-end ML platform, from feature engineering to real-time serving. We'll highlight the benefits of a centralized platform in accelerating model development cycles and improving reliability.
Elevating Search Relevance with SigLIP: The Power of Multimodal Retrieval
Explore how SigLIP, a cutting-edge multimodal model, revolutionizes search by unifying image and text data. Learn how leveraging joint vision-language understanding leads to smarter, more accurate, and context-aware search experiences, product attribution, surpassing traditional text-only methods for real-world applications.
Beyond Correlation: A Practical Guide to Causal Inference in Data Science
Causal inference answers questions beyond correlation, such as whether interventions truly cause outcomes. This session will introduce foundational concepts in causal inference and relevant Python tools. Attendees will leave with an improved intuition for how to use causal inference methods in applied data science.