Shopbots are agents that automatically search the Internet to obtain information about prices and other attributes of goods and services. They herald a future in which autonomous agents profoundly influence electronic markets. In this study, a simple economic model is proposed and analyzed, which is intended to quantify some of the likely impacts of a proliferation of shopbots and other economically-motivated software agents. In addition, this paper reports on simulations of pricebots - adaptive, pricesetting agents which firms may well implement to combat, or even take advantage of, the growing community of shopbots. This study forms part of a larger research program that aims to provide insights into the impact of agent technology on the nascent information economy.

We envision a future in which the global economy and the Internet will merge and evolve together into an information economy bustling with billions of economically motivated software agents that exchange information goods and services with humans and other agents. Economic software agents will differ in important ways from their human counterparts, and these differences may have significant beneficial or harmful effects upon the global economy. It is therefore important to consider the economic incentives and behaviors of economic software agents, and to use every available means to anticipate their collective interactions. We survey research conducted by the Information Economies group at IBM Research aimed at understanding collective interactions among agents that dynamically price information goods or services. In particular, we study the potential impact of widespread shopbot usage on prices, the price dynamics that may ensue from various mixtures of automated pricing ...

Web robots are software programs that automatically traverse the hyperlink structure of the World Wide Web in order to locate and retrieve information. There are many reasons why it is important to identify visits by the Web robots and distinguish them from other users. First of all, e-commerce retailers are particularly concerned about the unauthorized deployment of robots for gathering business intelligence at their Web sites. In addition, Web robots tend to consume considerable network bandwidth at the expense of other users. Sessions due to Web robots also make it more difficult to perform clickstream analysis effectively on the Web data. Conventional techniques for detecting Web robots are often based on identifying the IP address and user agent of the Web clients. While these techniques are applicable to many well-known robots, they may not be sufficient to detect camouaging and previously unknown robots. In this paper, we propose an alternative approach that uses the navigational patterns in the click-stream data to determine if it is due to a robot. Experimental results on our Computer Science department Web server logs show that highly accurate classification models can be built using this approach. We also show that these models are able to discover many camouflaging and previously unidentified robots.

Shopbots are software agents that automatically query multiple sellers on the Internet to gather information about prices and other attributes of consumer goods and services. Rapidly increasing in number and sophistication, shopbots are helping more and more buyers minimize expenditure and maximize satisfaction. In response at least partly to this trend, it is anticipated that sellers will come to rely on pricebots, automated agents that employ price-setting algorithms in an attempt to maximize profits. This paper reaches toward an understanding of strategic pricebot dynamics. More specifically, this paper is a comparative study of four candidate price-setting strategies that differ in informational and computational requirements: gametheoretic pricing (GT), myoptimal pricing (MY), derivative following (DF), and Q-learning (Q). In an effort to gain insights into the tradeoffs between practicality and pro tability of pricebot algorithms, the dynamic behavior that arises among homogeneous and heterogeneous collections of pricebots and shopbot-assisted buyers is analyzed and simulated. In homogeneous settings -- when all pricebots use the same pricing algorithm -- DFs outperform MYs and GTs. Investigation of heterogeneous collections of pricebots, however, reveals an incentive for individual DFs to deviate to MY or GT. The Q strategy exhibits superior performance to all the others since it learns to predict and account for the long-term consequences of its actions. Although the current implementation of Q is impractically expensive, techniques for achieving similar performance at greatly reduced computational cost are under investigation.

Abstract. In the last few years, there has been increasing interest from the agent community in the use of techniques from decision theory and game theory. Our aims in this article are firstly to briefly summarise the key concepts of decision theory and game theory, secondly to discuss how these tools are being applied in agent systems research, and finally to introduce this special issue of Autonomous Agents and Multi-Agent Systems by reviewing the papers that appear.

E-commerce will undoubtedly change the way business is done. But as we have said elsewhere, “technology changes, economic laws do not. ” Despite the changes introduced by e-commerce, many of the fundamental principles of competition will still be relevant. In this paper I investigate three aspects of competition in ecommerce: marketing, interconnection, and price matching. In each case I will describe the phenomenon, illustrate its relevance for ecommerce, and describe some research issues raised.

Abstract. We study the price dynamics in a multi-agent economy consisting of buyers and competing sellers, where each seller has limited information about its competitors ’ prices. In this economy, buyers use shopbots while the sellers employ automated pricing agents or pricebots. A pricebot resets its seller’s price at regular intervals with the objective of maximizing revenue in each time period. Derivative following provides a simple, albeit naive, strategy for dynamic pricing in such a scenario. In this paper, we refine the derivative following algorithm and introduce a model-optimizer algorithm that re-estimates the priceprofit relationship for a seller in each period more efficiently. Simulations using the model-optimizer algorithm indicate that it outperforms derivative following even though it does not have any additional information about the market. Our results underscore the role machine learning and optimization can play in fostering competition (or cooperation) in a multi-agent economy where the agents have limited information about their environment.

In recent years, it is becoming increasingly difficult to ignore the impact of Web robots on both commercial and institutional Web sites. Not only do Web robots consume valuable bandwidth and Web server resources, they are also making it more difficult to apply Web Mining techniques eectively on the Web logs. E-commerce Web sites are also concern about unauthorized deployment of shopbots for the purpose of gathering business intelligence at their Web sites. Ethical robots can be easily detected because they tend to follow most of the guidelines proposed for robot designers. On the other hand, unethical robots are more difficult to identify since they tend to camouage their entries in the Web logs. In this paper, we examine the problem of identifying navigational patterns of Web robots using conventional machine learning techniques. Our goal is to construct a predictive model that will distinguish between the browsing behavior of legitimate Web users from access patterns due to Web robots. Our results show that highly accurate models can be obtained using a small set of access features deduced from the Web logs.

this article, we refer to this type of changing of prices over time as dynamic pricing

It is frequently claimed that the growth of e-commerce has created a more competitive environment. It is argued that lower production costs of online retailers encourages new entry in previously concentrated sectors, and a marked reduction in search costs and switching costs increase the intensity of competition. The limited evidence that exists paints a more mixed picture. Many online markets tend to be advertising-intensive, creating a tendency towards concentration; search and price comparison are not perfect; firms can create product heterogeneity and raise switching costs to dampen price competition. Where firms have some market power, as in the market for information goods, we expect discriminatory pricing to become the norm. Apart from posted prices, the internet has extended the use of auctions, even to relatively low-value goods previously traded in thin local markets. The lowcost, relatively frictionless online auction markets have increased profits as well as economic efficiency, and may emerge as the principal pricing method for a large number of goods and services.