Business analytics instructors generate flexible synthetic datasets with ai
DataCanvas-EDU: An Agentic Framework for Instructor-Guided Synthetic Data Generation in Business Analytics Education
Human-Computer InteractionArtificial Intelligence
Summary
Business analytics teachers often need various datasets for different lessons, but real data can be hard to get and is not flexible. The authors created DataCanvas-EDU, a system where teachers talk to an AI to design synthetic datasets with specific patterns. The AI then writes code to create the data, checks it, and makes assignments and grading guides. This helps teachers save time and lets students work with unique data instead of familiar examples.
What this means in practice
- •For learning management system developers: Integrate instructor-guided synthetic data generation tools to create custom datasets and assignments for business analytics courses.$Commercial implications: This enables LMS platforms to offer tailored analytics course content with built-in AI data synthesis capabilities, enhancing course customization.
- •For corporate training teams: Create diverse, realistic synthetic datasets aligned with specific business scenarios for internal analytics training without exposing sensitive real data.
Authors
Bang An, Maria Hamdani, Joseph Fox
Abstract
Business analytics education requires diverse datasets to support different learning objectives, student backgrounds, and analytical tasks. Real-world data can be difficult to obtain and offer limited flexibility for adapting a case to a particular course. Even when suitable data are available, instructors must investigate the patterns, verify the results, and prepare assignments and reference solutions, requiring substantial time and effort. The use of large language models (LLMs) introduces an additional concern about training data contamination. Widely used public datasets often have extensive tutorials and worked analyses that models may have encountered during training. Students may therefore receive explanations drawn from existing analyses without practicing how to investigate unfamiliar data in collaboration with AI. This paper presents DataCanvas-EDU, an agentic framework for instructor-guided synthetic data generation in business analytics education. Instructors specify teaching goals and intended patterns through conversation, while an AI agent writes generation code, checks the resulting data, and prepares assignments, reference analyses, and rubrics. Four phases, Plan, Create, Verify / Test Analysis, and Evaluate, organize the process and support instructor review and revision. The framework is intended to simplify case preparation while creating opportunities for students to investigate newly designed patterns with AI. We illustrate the approach with WindowDash, a food delivery case containing 15,000 orders and nine designed patterns. DataCanvas-EDU is packaged as a reusable AI Agent Skill for compatible agent environments, with the package and installation instructions available at https://github.com/BANG23333/datacanvas-edu