Study of Articial Financial Markets with Adaptive Trading Agents

The Problem: The project aims to study various ways of designing intelligent trading and marketmaking agents. We will then study cooperative behavior of agents under previously developed articial nancial market environment. This research can give insights for designing general-purposed articial markets. Motivation: In the past years, we and others have developed some basic families of algorithmic components for coping with multiple aspects of learning. It is natural to probe directly into the evolution of intelligence and learning mechanisms and into the problem of distributed intelligence such as collective learning, coordination and competition. In this project, we focus on an agent-based modeling of articial markets: how software agents endowed with learning abilities might interact, co-evolve, and cooperate in societies of learning agents. Previous Work: The project draws on at least three distinct literatures: the market microstructure, the experimental markets, and the simulated markets. Studies in market microstructure provides important background and context for the experiments and simulations[6]. Another alternative to the theoretical approach is an experimental one in which individuals are placed in a controlled market setting, given certain endowments of securities and cash, and allowed to trade with each other.[2, 5] Lastly, computer simulations of markets populated by software agents extend the experimental approach by allowing the experimenter to test various theories of learning behavior and market microstructure in a controlled environment[4, 3]. Approach: Our proposed research consists of three complementary parts: 1. Articial Market Dynamics o Construction of articial nancial markets with adaptive trading and market-making agents whose behavior and performance are studied. 2. Theoretical and Computational Studies of Market Equilibrium o Study of theoretical reasoning