En savoir plus
This book provides an overview of agent-based modeling (ABM) and multi-agent systems (MAS), emphasizing their significance in understanding complex economic systems, with a special focus on the emerging properties of heterogeneous agents that cannot be deduced from the characteristics of individual agents. ABM is highlighted as a powerful tool for studying economics, especially in the context of financial crises and pandemics, where traditional models, such as dynamic stochastic general equilibrium (DSGE) models, have proven inadequate.
Containing numerous practical examples and applications with R, Python, Julia and Netlogo, the book explores how learning, particularly machine learning, can be integrated into multi-agent systems to enhance the adaptation and behavior of agents in dynamic environments. It compares different learning approaches, including game theory and artificial intelligence, highlighting the advantages of each in modeling economic phenomena.
Table des matières
Agent-Based Models and the Economics of Crisis.- The Machine Learning perspective.- Setting up Agent-Based Models of Crisis (Microeconomic Model of Crisis; Virus on a Network Spread Model).- Developing models with Python and R.
A propos de l'auteur
Anand Rao is a Distinguished Services Professor of Applied Data Science and AI in the Heinz College of Information Systems and Public Policy at Carnegie Mellon University. He received his PhD from the University of Sydney (with a University Postgraduate Research Award-UPRA) in 1988 and an MBA (with Award of Distinction) from Melbourne Business School in 1997. He boasts a 35-year career spanning AI, data, and analytics, serving as PwC's Global AI Leader. His research focuses on operationalizing AI, responsible AI, and agent-based models. Recognized globally, he has received accolades such as the Most Influential Paper Award and distinctions in AI and InsureTech. Prior to joining management consulting, he was the Chief Research Scientist at the Australian Artificial Intelligence Institute, where he built agent-based models and simulation systems and conducted research in the theory and practice of multi-agent systems.
Pedro Campos, PhD in Business Sciences (2008), with a background in Mathematics and Statistics, is Associate Professor of the Faculty of Economics, University of Porto, and conducts his research at LIAAD, the Artificial Intelligence and Decision Analysis Laboratory of INESC TEC. He currently serves as the Director of Methodology Services at Statistics Portugal. He specializes in Statistics, Data Science, Network Mining, and Marketing Research. Some of his research contributions delve into Innovation and Employment, Collaborative Networks, and Data Visualization. He has more than 50 publications, including articles in specialized journals and book chapters, and has edited 3 books. Pedro is also Deputy Director of the ISLP (International Statistical Literacy Project).
Joaquim Margarido, an ISEP (Superior Institute of Engineering of Porto) graduate, holds a master's degree in multi-agent systems. With expertise in IT, he imparts knowledge in programming using Java, Python, C#, SQL, and web technologies. Dedicated to practical solutions, Joaquim has developed software for various companies, addressing common challenges. His commitment to innovative software solutions reflects his extensive training and proficiency in diverse programming languages, contributing to both education and industry.
Résumé
This book provides an overview of agent-based modeling (ABM) and multi-agent systems (MAS), emphasizing their significance in understanding complex economic systems, with a special focus on the emerging properties of heterogeneous agents that cannot be deduced from the characteristics of individual agents. ABM is highlighted as a powerful tool for studying economics, especially in the context of financial crises and pandemics, where traditional models, such as dynamic stochastic general equilibrium (DSGE) models, have proven inadequate.
Containing numerous practical examples and applications with R, Python, Julia and Netlogo, the book explores how learning, particularly machine learning, can be integrated into multi-agent systems to enhance the adaptation and behavior of agents in dynamic environments. It compares different learning approaches, including game theory and artificial intelligence, highlighting the advantages of each in modeling economic phenomena.
