Innovative Data Sources and Tools: Generative AI

Class Materials

• Case: GPT_BackgroundCase
• Case: Innovation_mindset_case_studies_Swindle_in_the age_of_AI
• Link: Chat GPT (or use other LLM) for help with regular expressions
• Link: A Template for the Pure Oils Case Submission (Optional but helpful).
• Slides: PowerPoint or PDF
• Data: A data update may be required. Using cmd run git pull in the datasets.io folder.
• Analytics Tools: Chat GPT (or another LLM), Python, Visual Studio Code, Alteryx
• Suggested in-class seating: discussion teams

• Suggested Pre-Class Preparation

  1. The background reading and case can either be read in advance, or used as a reference.
  2. The case has been updated from a draft version, but the content is still largely the same, no need to re-read it, but we will use it as a reference in class.

• Class Plan

  1. We will start with a short discussion of GPTs and a practical way of using them in data analytics.
  2. We will first ask the GPT to provide a first pass at the requirements for the case. The output will be saved as the first attempt.
  3. In discussion teams we will examine the GPT data and look for indicators, or red flags, that the data is fake/AI generated and make a list of these indicators (this list will be the deliverable for this class).
  4. We will then refine our approach to the case by interacting with the GPT in building python code to execute the requirements.