Organizations deal with a wide range of inconsistent and semi structured inputs: mismatched field names, misaligned values, and context that isn’t standardized. This session presents a practical, production tested approach to AI driven attribute intelligence that automates three tricky steps in data readiness: detection, extraction, and standardization. Using our Data Attribution Detection framework, we’ll demonstrate how AI can read information from virtually any source - emails, spreadsheets, PDFs, forms, or free text messages - and convert it into clean, consistent, system ready outputs. We’ll walk through an end-to-end solution designed to reduce manual data prep while increasing trust, reproducibility, and downstream efficiency.
Attendees will see a real-world case study showing how we standardized thousands of attributes across disparate contexts, cut onboarding time, and raised downstream efficiency. We’ll also highlight the significant operational lift achieved by eliminating hours of manual reading, interpreting, reformatting, and reentering data into internal systems - steps that traditionally slow teams down and introduce inconsistency. Finally, we’ll show how these methods can be applied to other everyday data prep challenges.
Use with AI
Copy this session's complete context to paste into ChatGPT, Claude, or any AI assistant.
Preview context block
## Session: AI Attribute Intelligence: Automating Detection, Extraction, and Standardization at Scale **Track:** Production and Operations | **Time:** 1:20 PM–2:05 PM | **Room:** 275 | **Type:** Expert Talk **Conference:** CIRAS AI Summit for Iowa — May 6, 2026, Scheman Building, Iowa State University, Ames IA ### Speaker(s) **Zach Dygert** — Machine Learning Engineer, Principal (Des Moines, IA) Incomplete (Please Submit) **Justin Claycomb** — Assistant Director Data Science, Principal (Des Moines, IA) Justin Claycomb serves as the Assistant Director of Data Science at Principal, where he specializes in operationalizing AI and scaling analytics solutions across the enterprise. Over the past decade, he has led the development and deployment of high-impact models that drive measurable business outcomes. Justin holds master’s degrees in Analytics, Business Administration, and Social Sciences, and is currently pursuing his doctorate, further deepening his interdisciplinary expertise. He is driven by a commitment to turning complex data into clear, actionable insights and fostering a culture of data-informed decision-making. **Melissa Hollis** — Director Data & Analytics, Principal (Des Moines, IA) Melissa Hollis is the Director of Data Analytics at Principal Financial Group, where she leads the Applied AI and Analytics teams within the corporate division. Her work focuses on driving strategic initiatives, delivering insights across business units, and supporting enterprise-wide AI efforts. Melissa began her career as an actuary and transitioned into analytics eight years ago. She is passionate about continuous learning and applying emerging technologies to create meaningful, analytics-driven solutions. She holds degrees in actuarial science, has completed law school, and earned a master’s in data science, bringing a unique interdisciplinary perspective to her work. | | | | ### Session Description Organizations deal with a wide range of inconsistent and semi structured inputs: mismatched field names, misaligned values, and context that isn’t standardized. This session presents a practical, production tested approach to AI driven attribute intelligence that automates three tricky steps in data readiness: detection, extraction, and standardization. Using our Data Attribution Detection framework, we’ll demonstrate how AI can read information from virtually any source - emails, spreadsheets, PDFs, forms, or free text messages - and convert it into clean, consistent, system ready outputs. We’ll walk through an end-to-end solution designed to reduce manual data prep while increasing trust, reproducibility, and downstream efficiency. Attendees will see a real-world case study showing how we standardized thousands of attributes across disparate contexts, cut onboarding time, and raised downstream efficiency. We’ll also highlight the significant operational lift achieved by eliminating hours of manual reading, interpreting, reformatting, and reentering data into internal systems - steps that traditionally slow teams down and introduce inconsistency. Finally, we’ll show how these methods can be applied to other everyday data prep challenges. ### Other sessions in the Production and Operations track - Vision AI Efforts in Attribute Detections and Measurements (3:10 PM–3:55 PM) - Natural Language Search for Member Benefits (3:10 PM–3:55 PM) - Industrial AI Success Stories: Because Even My Title Needed Machine Learning (10:20 AM–11:05 AM) - Tabular Foundation Models Meet Manufacturing: A Practical Exploration (11:15 AM–12:00 PM) ### Suggested prompts for this session - "What questions should I prepare to ask the speaker(s) at this session?" - "Create a structured note-taking template for this session focused on actionable takeaways" - "Based on this session description, what background reading should I do to get the most value?" - "After I attend, help me create an action plan for implementing what I learned" - "How does this session connect to the other sessions in the Production and Operations track?"