|
Module 1: Introduction to AI in Data Analysis
|
|
|
|
Role of ChatGPT in enhancing data analysis workflows
|
|
|
|
Understanding capabilities and limitations of GPT for analysis
|
|
|
|
CODEpy
|
|
|
Module 2: Structuring Data-Driven Questions for GPT
|
|
|
|
How to frame effective prompts for data understanding
|
|
|
|
Asking GPT to explain data trends, patterns, and metrics
|
|
|
Module 3: Data Cleaning and Preparation with ChatGPT
|
|
|
|
Guidance for cleaning messy datasets
|
|
|
|
Prompting ChatGPT to suggest preprocessing steps
|
|
|
Module 4: Exploratory Data Analysis (EDA) Support
|
|
|
|
Using GPT to generate EDA questions and interpretations
|
|
|
|
Describing distributions, trends, and outliers with AI help
|
|
|
Module 5: Writing Code with ChatGPT (Python/Excel/SQL)
|
|
|
|
Using GPT to generate Python, Excel, or SQL snippets
|
|
|
|
Examples: filtering data, creating pivot tables, summarizing metrics
|
|
|
Module 6: Interpreting Analytical Results
|
|
|
|
Explaining statistical output with GPT assistance
|
|
|
|
Asking GPT to summarize insights for presentations or reports
|
|
|
Module 7: Automating Report Generation
|
|
|
|
Prompting ChatGPT to write insights, summaries, or dashboards
|
|
|
|
Creating natural-language executive summaries
|
|
|
Module 8: Business Scenario-Based Analysis
|
|
|
|
Case studies: sales data, marketing performance, customer churn
|
|
|
|
Simulating problem-solving with AI prompts
|
|
|
Module 9: Ethical Use and Accuracy Check
|
|
|
|
Validating AI-generated insights
|
|
|
|
Responsible use of AI for business decisions
|
|