Table of Contents:
  • 1. Introduction
  • 1.1 The premise
  • 1.2 Prediction tasks taxonomy
  • 1.3 Exercises
  • 2. Utility maximization paradigm
  • 2.1 Single decision-maker-decision theory
  • 2.1.1 Decision-making under certainty
  • 2.1.2 Decision-making under uncertainty
  • 2.2 Multiple decision-makers-game theory
  • 2.2.1 Normal form games
  • 2.2.2 Extensive form games
  • 2.3 Are people rational? A short note
  • 2.4 Exercises
  • 3. Predicting human decision-making
  • 3.1 Expert-driven paradigm
  • 3.1.1 Utility maximization
  • 3.1.2 Quantal response
  • 3.1.3 Level-k
  • 3.1.4 Cognitive hierarchy
  • 3.1.5 Behavioral sciences
  • 3.1.6 Prospect theory
  • 3.1.7 Utilizing expert-driven models
  • 3.2 Data-driven paradigm
  • 3.2.1 Machine learning: a human prediction perspective
  • 3.2.2 Deep learning, the great redeemer?
  • 3.2.3 Data, the great barrier?
  • 3.2.4 Additional aspects in data collection
  • 3.2.5 The data frontier
  • 3.2.6 Imbalanced datasets
  • 3.2.7 Levels of specialization: who and what to model
  • 3.2.8 Transfer learning
  • 3.3 Hybrid approach
  • 3.3.1 Expert-driven features in machine learning
  • 3.3.2 Additional techniques for combining expert-driven and data-driven models
  • 3.4 Exercises
  • 4. From human prediction to intelligent agents
  • 4.1 Prediction models in agent design
  • 4.2 Security games
  • 4.3 Negotiations
  • 4.4 Argumentation
  • 4.5 Voting
  • 4.6 Automotive industry
  • 4.7 Games that people play
  • 4.8 Exercises
  • 5. Which model should I use?
  • 5.1 Is this a good prediction model?
  • 5.2 The predicting human decision-making (PHD) flow graph
  • 5.3 Ethical considerations
  • 5.4 Exercises
  • 6. Concluding remarks
  • Bibliography
  • Authors' biographies
  • Index.