Predicting Human Decision-Making

Book description

Human decision-making often transcends our formal models of "rationality." Designing intelligent agents that interact proficiently with people necessitates the modeling of human behavior and the prediction of their decisions. In this book, we explore the task of automatically predicting human decision-making and its use in designing intelligent human-aware automated computer systems of varying natures—from purely conflicting interaction settings (e.g., security and games) to fully cooperative interaction settings (e.g., autonomous driving and personal robotic assistants). We explore the techniques, algorithms, and empirical methodologies for meeting the challenges that arise from the above tasks and illustrate major benefits from the use of these computational solutions in real-world application domains such as security, negotiations, argumentative interactions, voting systems, autonomous driving, and games. The book presents both the traditional and classical methods as well as the most recent and cutting edge advances, providing the reader with a panorama of the challenges and solutions in predicting human decision-making.

Table of contents

  1. Cover
  2. Copyright
  3. Title Page
  4. Contents
  5. Preface
  6. Acknowledgments
  7. 1 Introduction
    1. 1.1 The Premise
    2. 1.2 Prediction Tasks Taxonomy
    3. 1.3 Exercises
  8. 2 Utility Maximization Paradigm
    1. 2.1 Single Decision-Maker–Decision Theory
      1. 2.1.1 Decision-Making Under Certainty
      2. 2.1.2 Decision-Making Under Uncertainty
    2. 2.2 Multiple Decision-Makers–Game Theory
      1. 2.2.1 Normal Form Games
      2. 2.2.2 Extensive Form Games
    3. 2.3 Are People Rational? A Short Note
    4. 2.4 Exercises
  9. 3 Predicting Human Decision-Making
    1. 3.1 Expert-Driven Paradigm
      1. 3.1.1 Utility Maximization
      2. 3.1.2 Quantal Response
      3. 3.1.3 Level-k
      4. 3.1.4 Cognitive Hierarchy
      5. 3.1.5 Behavioral Sciences
      6. 3.1.6 Prospect Theory
      7. 3.1.7 Utilizing Expert-Driven Models
    2. 3.2 Data-Driven Paradigm
      1. 3.2.1 Machine Learning: A Human Prediction Perspective
      2. 3.2.2 Deep Learning—The Great Redeemer?
      3. 3.2.3 Data—The Great Barrier?
      4. 3.2.4 Additional Aspects in Data Collection
      5. 3.2.5 The Data Frontier
      6. 3.2.6 Imbalanced Datasets
      7. 3.2.7 Levels of Specialization: Who and What to Model
      8. 3.2.8 Transfer Learning
    3. 3.3 Hybrid Approach
      1. 3.3.1 Expert-Driven Features in Machine Learning
      2. 3.3.2 Additional Techniques For Combining Expert-Driven and Data-Driven Models
    4. 3.4 Exercises
  10. 4 From Human Prediction to Intelligent Agents
    1. 4.1 Prediction Models in Agent Design
    2. 4.2 Security Games
    3. 4.3 Negotiations
    4. 4.4 Argumentation
    5. 4.5 Voting
    6. 4.6 Automotive Industry
    7. 4.7 Games That People Play
    8. 4.8 Exercises
  11. 5 Which Model Should I Use?
    1. 5.1 Is This a Good Prediction Model?
    2. 5.2 The Predicting Human Decision-making (PHD) Flow Graph
    3. 5.3 Ethical Considerations
    4. 5.4 Exercises
  12. 6 Concluding Remarks
  13. Bibliography
  14. Authors’ Biographies
  15. Index

Product information

  • Title: Predicting Human Decision-Making
  • Author(s): Ariel Rosenfeld, Sarit Kraus, Ronald Brachman, Peter Stone
  • Release date: January 2018
  • Publisher(s): Morgan & Claypool Publishers
  • ISBN: 9781681733289