Understanding the Problem

  Decomposing the Problem Using Decision Tree (DT) Framework

  Analytic Approach

  Data Requirements

  Data Collection

  Modelling Approach

  Validating Model Quality: Test-Train Split, Cross-Validation

  Model Quality Metrics: RMSE, MSE, MAPE

  Introduction to Commonly Used Algorithms

  Storytelling with Data and Model Insights

Different Aspects of a Model: Train, Test, Validate

  Understanding Hyperparameters

  Common Platforms for Building and Running Models

  Recommended Tools

  Introduction to Platforms (e.g., Watson)

  AI Model Lifecycle: Build, Deploy, Retrain

The Need for Storytelling

• Importance of Storytelling
• Information Processing and Recall
• Structuring the Story

  How to Create Stories

• Pen-Paper Approach
• Identifying the Sole Purpose
• Using Powerful Headings

  Stories During Predictive Modeling Steps

• Data Exploration
• Feature Visualization
• Model Creation
• Model Comparisons

  Best Practices of Storytelling

• Designing a Roadmap
• Concluding with Brevity

  Ethics of Storytelling

  Types of Data and Suitable Charts

• Text: Word Clouds
• Mixed: Facet Grids
• Numeric: Line/Bar Charts
• Stocks: Candlestick Charts
• Geographic: Maps

• Communication Skills
• Self-management Skills
• Information and Communication Technology Skills
• Entrepreneurial Skills
• Green Skills