Intelligent Agents in Portfolio Management

Abstract

Due to advances in technology, diverse and voluminous information is becoming available to decision makers. This presents the potential for improved decision support, but poses challenges in terms of building tools to support users in accessing, filtering, evaluating, and fusing information from heterogeneous information sources. Most reported research on intelligent information agents to date has dealt with a user interacting with a single agent that has general knowledge and is capable of performing a variety of user delegated information finding tasks (e.g., Etzioni and Weld, 1994). For each information query, the agent is responsible for accessing different information sources and integrating the results. We believe that, given the current computational state of the art, a centralized agent approach has many limitations: (1) a single general agent would need an enormous amount of knowledge to be able to deal effectively with user information requests that cover a variety of tasks, (2) a centralized information agent constitutes a processing bottleneck and a ‘single point of failure,’ (3) unless the agent has beyond the state of the art learning capabilities, it would need considerable reprogramming to deal with the appearance of new agents and information sources in the environment, (4) because of the complexity of the information fmding and filtering task, and the large amount of information, the required processing would overwhelm a single agent. For these reasons and because of the characteristics of the Internet environment, we employ a distributed collaborative collection of agents for information gathering.