INFORMS Analytics 2026 Workshop Using Generative AI in Analytics: Demonstration, Pitfalls, and Practices
Date:
Generative AI promises to transform the practice of analytics, however, the foundation models, trained on readily available data, fails in situations that experts would recognize but novices would not. In analytics projects where context and nuance are important this leads to faulty analysis and failed projects. This workshop will demonstrate using Generative AI through the steps of the INFORMS Analytics Framework, with special attention to enabling good communication between the analyst, subject matter experts, and decision makers who will use analytical products. Specifically, Generative AI will be used to enable clear communications between stakeholders and analysts. It will use project artifacts such as Product Requirements Documents, mathematical formulations, and implemented models to enable all stakeholders to verify that analytical products meet project requirements. Finally, use Generative AI to present results for a range of different stakeholders. The workshop will be done using Gemini NotebookLM, but can be followed using any Generative AI persistent workspace tool (e.g. Gemini NotebookLM, Gems, Claude Projects, OpenAI Custom GPTs, or Copilot Agents) or terminal based tools (e.g. Gemini CLI, Claude Code, or OpenAI Codex). While the workshop will implement models as project artifacts, Generative AI will be used to translate back and forth to domain language so programming and modeling knowledge is not necessary.