Abstract—This paper surveys and analyzes the state of the art of agent-mediated electronic commerce (e-commerce), concentrating particularly on the business-to-consumer (B2C) and business-to-business (B2B) aspects. From the consumer buying behavior perspective, agents are being used in the following activities: need identification, product brokering, buyer coalition formation, merchant brokering, and negotiation. The roles of agents in B2B e-commerce are discussed through the business-to-business transaction model that identifies agents as being employed in partnership formation, brokering, and negotiation. Having identified the roles for agents in B2C and B2B e-commerce, some of the key underpinning technologies of this vision are highlighted. Finally, we conclude by discussing the future directions and potential impediments to the wide-scale adoption of agent-mediated e-commerce. Index Terms—Agent-mediated electronic commerce, intelligent agents. 1

Abstract. This paper describes the design and evaluation of SouthamptonSCM,

We develop a novel bidding strategy that software agents can use to buy and sell goods in Continuous Double Auctions (CDAs). Our strategy involves the agent forming a bid or ask by assessing the degree of risk involved and making a prediction about the competitive equilibrium that is likely to be reached in the marketplace. We benchmark our strategy against two of the most common strategies for CDAs, namely the Zero-Intelligence and the ZeroIntelligence Plus strategies, and we show that our agents outperform these benchmarks. Specifically, our agents win in 100% of the simulations against the ZI agents and, on average, 75% of the games against the ZIP agents.

Software agents are increasingly being used to represent humans in online auctions. Such agents have the advantages of being able to systematically monitor a wide variety of auctions and then make rapid decisions about what bids to place in what auctions. They can do this continuously and repetitively without losing concentration. To provide a means of evaluating and comparing (benchmarking) research methods in this area the trading agent competition (TAC) was established. This competition involves a number of agents bidding against one another in a number of related auctions (operating different protocols) to purchase travel packages for customers. Against this background, this paper describes the design, implementation and evaluation of SouthamptonTAC, one of the most successful participants in both the Second and the Third International Competitions. Our agent uses fuzzy techniques at the heart of its decision making: to make bidding decisions in the face of uncertainty, to make predictions about the likely outcomes of auctions, and to alter the agent's bidding strategy in response to the prevailing market conditions.

The increasing prevalence of auctions as a method of conducting a variety of transactions has promoted interest in modelling bidding behaviours with simulated agent models. The majority of popular research has focused on double auctions, i.e. auctions with multiple buyers and sellers. In this paper we investigate agent models of sealed bid auctions, i.e. single seller auctions where each buyer submits a single bid. We propose an adaptation of two learning mechanisms used in double auctions, Zero Intelligence Plus (ZIP) and Gjerstad-Dickhaut (GD), for sealed bid auctions. The experimental results determine if a single agent adopting ZIP & GD bidding mechanisms is able to learn the known optimal strategy through experience. We experiment with two types of sealed bid auctions, first price sealed bid and second price sealed bid. Quantitive analysis shows that whilst ZIP agents learn a good strategy they do not learn the optimal strategy, whereas GD agents learn an optimal strategy in first price auctions.

As computational agents are developed for increasingly complicated e-commerce applications, the complexity of the decisions they face demands advances in artificial intelligence techniques. For example, an agent representing a seller in an auction should try to maximize the seller’s profit by reasoning about a variety of possibly uncertain pieces of information, such as the maximum prices various buyers might be willing to pay, the possible prices being offered by competing sellers, the rules by which the auction operates, the dynamic arrival and matching of offers to buy and sell, and so on. A naïve application of multiagent reasoning techniques would require the seller’s agent to explicitly model all of the other agents through an extended time horizon, rendering the problem intractable for many realistically-sized problems. We have instead devised a new strategy that an agent can use to determine its bid price based on a more tractable Markov chain model of the auction process. We have experimentally identified the conditions under which our new strategy works well, as well as how well it works in comparison to the optimal performance the agent could have achieved had it known the future. Our results show that our new strategy in general performs well, outperforming other tractable heuristic strategies in a majority of experiments, and is particularly effective in a “seller’s market, ” where many buy offers are available. 1.

Abstract — This paper reports on the design and comparison of two economically-inspired mechanisms for task allocation in environments where sellers have finite production capacities and a cost structure composed of a fixed overhead cost and a constant marginal cost. Such mechanisms are required when a system consists of multiple self-interested stakeholders that each possess private information that is relevant to solving a system-wide problem. Against this background, we first develop a computationally tractable centralised mechanism that finds the set of producers that have the lowest total cost in providing a certain demand (i.e. it is efficient). We achieve this by extending the standard Vickrey-Clarke-Groves mechanism to allow for multi-attribute bids and by introducing a novel penalty scheme such that producers are incentivised to truthfully report their capacities and their costs. Furthermore our extended mechanism is able to handle sellers ’ uncertainty about their production capacity and ensures that individual agents find it profitable to participate in the mechanism. However, since this first mechanism is centralised, we also develop a complementary decentralised mechanism based around the continuous double auction. Again because of the characteristics of our domain, we need to extend the standard form of this protocol by introducing a novel clearing rule based around an order book. With this modified protocol, we empirically demonstrate (with simple trading strategies) that the mechanism achieves high efficiency. In particular, despite this simplicity, the traders can still derive a profit from the market which makes our mechanism attractive since these results are a likely lower bound on their expected returns. Index Terms — distributed decision making, decision theory, multi-agent systems, market-based control. I.

The “ZIP ” adaptive automated trading algorithm has been demonstrated to outperform human traders in experimental studies of continuous double auction (CDA) markets populated by mixtures of human and “software robot ” traders. Previous papers have shown that values of the eight parameters governing behavior of ZIP traders can be automatically optimized using a genetic algorithm (GA), and that markets populated by GA-optimized traders perform better than those populated by ZIP traders with manually-set parameter values. This paper introduces a more sophisticated version of the ZIP algorithm, called “ZIP60”, which requires the values of 60 parameters to be set correctly. ZIP60 is shown here to produce significantly better results in comparison to the original ZIP algorithm (called “ZIP8 ” hereafter) when a GA is used to search the 60-dimensional parameter space. It is also demonstrated here that this works best when the GA itself has control over the dimensionality of the search-space, allowing evolution to guide the expansion of the search-space up from 8 parameters to 60 via intermediate steps. Principal component analysis of the best evolved ZIP60 parameter-sets establishes that no ZIP8 solutions are embedded in the 60-dimensional space. Moreover, some of the results and analysis presented here

We present a general methodology to automate the search for equilibrium strategies in games derived from computational experimentation. Our approach interleaves empirical game-theoretic analysis with reinforcement learning. We apply this methodology to the classic Continuous Double Auction game, conducting the most comprehensive CDA strategic study published to date. Empirical game analysis confirms prior findings about the relative performance of known strategies. Reinforcement learning derives new bidding strategies from the empirical equilibrium environment. Iterative application of this approach yields strategies stronger than any other published CDA bidding policy, culminating in a new Nash equilibrium supported exclusively by our learned strategies.

Online auctions have become a popular method for business transactions. The variety of different auction rules, the restrictions in supply or demand, and the agents ’ com-binatorial preferences for the different commodities, have led to the creation of a very complex multi-agent “environment ” and a number of strategic tradeoffs. Designing an agent that deals efficiently with these tradeoffs has been a multi-pronged effort. Us-ing game-theoretic approaches, some equilibria have been computed for relatively sim-ple auctions. However, since these equilibria have limited practical application, due to the significant number of varying auctions that take place simultaneously, empiri-cal approaches and experimental evaluations of various strategies have also been used. Furthermore, progress has been made into designing better agent architectures. This dissertation presents results in all of these directions (theoretical and empiri-cal). We present a methodology for designing trading agents, and deciding their bidding strategy, when they participate in a large number of simultaneous auctions with a variety of rules. We use a modular, adaptive, scalable and robust agent architecture, combining principled methods and empirical knowledge. We decompose the problem faced by the