发表机构
University of Akron（阿克伦大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出DataCanvas-EDU，一个教师引导的合成数据生成智能体框架，通过对话指定教学目标和模式，自动生成数据、作业和评分标准，简化案例准备并促进学生在AI协作下探究新数据模式。
AI 中文摘要
商业分析教育需要多样化的数据集，以支持不同的学习目标、学生背景和分析任务。真实世界的数据可能难以获取，并且在将案例适配到特定课程时灵活性有限。即使有合适的数据可用，教师也必须探究数据模式、验证结果并准备作业和参考答案，这需要大量的时间和精力。大型语言模型（LLMs）的使用还引入了关于训练数据污染的额外担忧。广泛使用的公开数据集通常带有大量教程和已分析示例，模型可能在训练过程中遇到过这些内容。因此，学生可能会获得来自现有分析的解答，而没有练习如何在人工智能的协作下探究不熟悉的数据。本文提出了DataCanvas-EDU，一个用于商业分析教育中教师引导式合成数据生成的智能体框架。教师通过对话指定教学目标和预期模式，而人工智能智能体编写生成代码、检查生成的数据，并准备作业、参考分析和评分标准。四个阶段——计划（Plan）、创建（Create）、验证/测试分析（Verify / Test Analysis）和评估（Evaluate）——组织整个流程，并支持教师审查和修订。该框架旨在简化案例准备，同时为学生创造机会，让他们与人工智能一起探究新设计的模式。我们通过WindowDash（一个包含15,000条订单和九种设计模式的外卖案例）来展示该方法。DataCanvas-EDU被打包为一种可复用的AI Agent Skill，适用于兼容的智能体环境，软件包和安装说明可在https URL获取。
英文摘要
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
CommentsSynthetic Dataset, Agentic Framework, Data Analytics Education, Data Visualization
