Agents that react to changing market situations

Market-driven agents are negotiation agents that react to changing market situations by making adjustable rates of concession. This paper presents 1) the foundations for designing market-driven strategies of agents, 2) a testbed of market-driven agents, 3) experimental results in simulating the market-driven approach, and 4) theoretical analyses of agents' performance in extremely large markets. In determining the amount of concession for each trading cycle, market-driven agents in this research are guided by four mathematical functions of eagerness, remaining trading time, trading opportunity , and competition. At different stages of trading, agents may adopt different trading strategies, and make different rates of concession. Four classes of strategies with respect to remaining trading time are discussed. Trading opportunity is determined by considering: 1) number of trading partners, 2) spreads-differences in utilities between an agent and its trading partners, and 3) probability of completing a deal. While eagerness represents an agent's desire to trade, trading competition is determined by the probability that it is not considered as the most preferred trader by its trading partners. Experimental results and theoretical analyses showed that agents guided by market-driven strategies 1) react to changing market situations by making prudent and appropriate rates of concession, and 2) achieve trading outcomes that correspond to intuitions in real-life trading.     

一种基于市场驱动的Multi-agent自动谈判策略

针对当前电子商务中基于Agent的谈判系统的谈判策略的静态性问题,提出基于市场驱动的谈判策略。Agent在谈判中能根据变化的市场情况做出可以调整比率的让步,帮助用户做出最优的交易决策,且自动地选择合适的策略。实验结果表明,采用基于市场驱动的策略比采用固定的策略的谈判结果更让用户感到满意。     

Equilibria, prudent compromises, and the "waiting" game.

While evaluation of many e-negotiation agents are carried out through empirical studies, this work supplements and complements existing literature by analyzing the problem of designing market-driven agents (MDAs) in terms of equilibrium points and stable strategies. MDAs are negotiation agents designed to make prudent compromises taking into account factors such as time preference, outside option, and rivalry. This work shows that 1) in a given market situation, an MDA negotiates optimally because it makes minimally sufficient concession, and 2) by modeling negotiation of MDAs as a game gamma of incomplete information, it is shown that the strategies adopted by MDAs are stable. In a bilateral negotiation, it is proven that the strategy pair of two MDAs forms a sequential equilibrium for gamma. In a multilateral negotiation, it is shown that the strategy profile of MDAs forms a market equilibrium for gamma.     

Toward market-driven agents for electronic auction

While there are several existing agent-based systems addressing the crucial and difficult issues of automated negotiation and auction, this research has designed and engineered a society of trading agents with two distinguishing features: 1) a market-driven negotiation strategy and 2) a deal optimizing auction protocol. Unlike some of the existing systems where users manually select predefined trading strategies, in the market-driven approach, trading agents automatically select the appropriate strategies by examining the changing market situations. Results from a series of experiments suggest that the market-driven approach generally achieved more favorable outcomes as compared to the fixed strategy approach. Furthermore, it provides a more intuitive simulation of trading because trading agents are able to respond to different market situations with appropriate strategies. By augmenting the auction protocol with a deal optimization stage, trading agents can be programmed to optimize transaction deals by delaying the finalization of deals in search of better deals. Experimental results showed that by having a deal optimization stage, the auction protocol produced generally optimistic outcomes     

Grid commerce, market-driven G-negotiation, and Grid resource management.

Although the management of resources is essential for realizing a computational grid, providing an efficient resource allocation mechanism is a complex undertaking. Since Grid providers and consumers may be independent bodies, negotiation among them is necessary. The contribution of this paper is showing that market-driven agents (MDAs) are appropriate tools for Grid resource negotiation. MDAs are e-negotiation agents designed with the flexibility of: 1) making adjustable amounts of concession taking into account market rivalry, outside options, and time preferences and 2) relaxing bargaining terms in the face of intense pressure. A heterogeneous testbed consisting of several types of e-negotiation agents to simulate a Grid computing environment was developed. It compares the performance of MDAs against other e-negotiation agents (e.g., Kasbah) in a Grid-commerce environment. Empirical results show that MDAs generally achieve: 1) higher budget efficiencies in many market situations than other e-negotiation agents in the testbed and 2) higher success rates in acquiring Grid resources under high Grid loadings.     

A Market–Driven Model for Designing Negotiation Agents

Although there are many extant agent–based systems for negotiation in e–commerce, the negotiation strategies of agents in these systems are mostly static. This article presents a model for designing negotiation agents that make adjustable rates of concession by reacting to changing market situations. To determine the amount of concession for each trading cycle, these market–driven agents are guided by four mathematical functions of eagerness, trading time, trading opportunity , and competition . Trading opportunity is determined by considering: (i) number of trading partners, (ii) spreads —differences in utilities between an agent and its trading partners, and (iii) probability of completing a deal. Competition is determined by the probability that an agent is not considered the most preferred trader by other negotiating parties. Motivated by factors such as corporate policies and resource needs, eagerness represents an agent's desire to complete a deal. Agents with different time sensitivity to deadlines employ different trading strategies by making different rates of concession at different stages of negotiation. In this article, three classes of strategies with respect to remaining trading time are discussed. Theoretical analyses show that market–driven agents are designed to make prudent and appropriate amounts of concession for a given market situation.     

Contracting With Uncertain Level Of Trust

The paper investigates the impact of trust on market efficiency and bilateral contracts. We prove that a market in which agents are trusted to the degree they deserve to be trusted is as efficient as a market with complete trustworthiness. In other words, complete trustworthiness is not a necessary condition for market efficiency. We prove that distrust could significantly reduce market efficiency, and we show how to solve the problem by using appropriately designed multiagent contracts. The problem of trust is studied in the context of a bilateral negotiation game between a buyer and a seller. It is shown that if the seller's trust equals the buyer's trustworthiness, then the social welfare, the amount of trade, and the agents' utility functions are maximized. The paper also studies the efficiency of advance payment contracts as a tool for improving trustworthiness. It is proved that advance payment contracts maximize the social welfare and the amount of trade. Finally, the paper studies the problem of how to make agents truthfully reveal their level of trustworthiness. An incentive–compatible contract is defined, in which agents do not benefit from lying about their trustworthiness. The analysis and the solutions proposed in this paper could help agent designers avoid many market failures and produce efficient interaction mechanisms.     

Inter-agent Dialogues in Electronic Marketplaces

This paper presents an overall framework for carrying out different types of dialogues between intelligent and autonomous agents acting in an electronic marketplace. Such dialogues take place during various commercial transactions concerning requests and offers of products and services. The proposed dialogue framework has been adopted in the communication and collaboration protocols of an already implemented system, which enables buyers and sellers delegate a variety of tasks to their personal agents. Much attention has been paid to the personalization of collaborative agents, which may permanently live and interact in the market representing their owners' interests. Our overall approach builds on a modular decomposition of the agents involved, and a formal and operational modeling of the associated dialogues. Features of our framework are demonstrated through an illustrative example of dialogues deployed during interagent transactions on the establishment of a combined reservation for dinner and a movie. The main contribution of this work is that the proposed framework is capable to represent disparate dialogues taking place among agents having adopted diverse strategies for carrying out e-commerce transactions.     

Electronic multilateral trade of electricity

This paper presents a technical approach for electronic multilateral trade of electricity in competitive power industries. The trade involves strategic sharing of data among agents in an attempt to provide the opportunity to intelligently discover competitive behavior of peer suppliers. A trading logic is implemented as a specialized software module within the agent. The logic mimics intelligence of the human strategic trade. A time-bounded trade protocol has been introduced as a trading basis among rivalry trade agents in the market. The protocol limits the trade rounds in order to bind the trading process to specific deadlines. The protocol is coded as part of the automated trade server. The results of a generic 3-bus test system show that the electronic multilateral trade logic presented in this paper better distributes market sales, lowers prices and consequently provides higher social welfare compared to the standard Cournot economic model that may be used by the human decision-maker for market trading. Based on a set of test cases with different load profiles, it is noted that the electronic multilateral trade drives the market price closer to the marginal cost of generation supply and far away from the estimated Cournot price.     

Bargaining on an Internet Agent-based Market: Behavioral vs. Optimizing Agents

In this paper, we analyze an Internet agent-based market where non-cooperative agents using behavioral rules negotiate the price of a given product in a bilateral and sequential manner. In this setting, we study the optimal decision-making process of a buying agent that enters the market. Our approach is based on Negotiation Analysis (Raiffa, 1982; Sebenuis, 1992) and we consider that the optimizing buying agent maximizes her discounted expected utility using subjective probabilities. The optimal decision-making process of the buying agent is treated as a stochastic control problem that can be solved by dynamic programming. Three types of behavioral agents are studied, namely conceder agents, boulware agents and imitative agents. A set of simulations is undertaken in order to predict the average outcome in a negotiation process for different parameters of the optimizing buying agent and for the three possible selling agents' behaviors. Finally, we compare the performance of the optimizing agent with that of behavioral buying agents.     

Bilateral Trade and ‘Small-World’ Networks

Trade requires search, negotiation, and exchange, which are activities thatabsorb resources. Thispaper investigates how different trade networks attend to these activities.An artificial marketis constructed in which autonomous agents endowed with a stock of goods seekout partners,negotiate a price, and then trade with the agent offering the best deal.Different trade networksare imposed on the system by restricting the set of individuals with whom anagent cancommunicate. We then compare the path to the eventual equilibrium as well asthe equilibriumcharacteristics of each trade network to see how each system dealt with thetasks of search,negotiation, and exchange.Initially, all agents are free to trade with any individual in the globalmarket. In such a world,global resources are optimally allocated with few trades, but only after atremendous amount ofsearch and negotiation. If trade is restricted within disjoint localboundaries, search is simple butglobal efficiency elusive. However, a hybrid model in which most agents tradelocally but a fewagents trade globally results in an economy that quickly reaches a Paretooptimal equilibriumwith significantly lower search and negotiation costs. Such small-worldnetworks occur innature and may help explain the ease with which most of us acquire goods fromaround theworld. We also show that there are private incentives for such a system toarise.     

Pricing strategies for dual‐channel supply chains under a trade credit policy

This paper discusses the impact of a trade credit policy on alleviating conflicts arising on a dual‐channel supply chain that includes one manufacturer and one value‐added retailer. We use the Stackelberg game to model the problem and characterize optimal pricing strategies for each supply chain partner, examining different circumstances in terms of retail price and trade credit contracts. When a consistent price strategy is applied in the dual channels under conditions of an exogenous credit period, trade credit can help both partners to achieve win‐win situations in the following circumstances: (1) when the retail channel's market share is small and the retailer's interest rate is high; or (2) when the retail channel's market share is large and the retailer's interest rate is lower than the manufacturer's. The study also concludes that when an inconsistent price strategy is applied, a trade credit contract can alleviate channel conflicts when the retailer's interest rate is higher than the manufacturer's. Otherwise, the partners may terminate cooperation. However, when the manufacturer has the power to determine and set the credit period, trade credit cannot alleviate channel conflicts under consistent price and inconsistent price scenarios.     

Automated traders in commodities markets: Case of producer–consumer institution

Automatizing commodities’ price negotiation was hard to achieve in practice, mainly because of logistical complications. The purpose of our work is to show that it is possible to automatize thoroughly commodities’ trading in the futures market by replacing human traders with artificial agents. As a starting step, we designed a market institution, called producer–consumer, where only an automated seller and an automated buyer can trade on behalf of the producer and consumer, respectively. The producer and consumer periodically feed their trading agents with supply and demand (S&D) forecasts. We suggested a parameterizable trading strategy, called bands and frequencies, for the agents. To measure the overall efficiency of this trading system in terms of price stability and liquidity, we made some hypotheses on the benchmark price curve and its linkages to S&D curves and other relevant market variables. Then we proposed analytical tools to measure strategy performance. Finally, we conducted some computer simulations to prove the workability of this approach.     

A context-aware approach to automated negotiation using reinforcement learning

Agents negotiate depending on individual perceptions of facts, events, trends and special circumstances that define the negotiation context. The negotiation context affects in different ways each agent’s preferences, bargaining strategies and resulting benefits, given the possible negotiation outcomes. Despite the relevance of the context, the existing literature on automated negotiation is scarce about how to account for it in learning and adapting negotiation strategies. In this paper, a novel contextual representation of the negotiation setting is proposed, where an agent resorts to private and public data to negotiate using an individual perception of its necessity and risk. A context-aware negotiation agent that learns through Self-Play and Reinforcement Learning (RL) how to use key contextual information to gain a competitive edge over its opponents is discussed in two levels of temporal abstraction. Learning to negotiate in an Eco-Industrial Park (EIP) is presented as a case study. In the Peer-to-Peer (P2P) market of an EIP, two instances of context-aware agents, in the roles of a buyer and a seller, are set to bilaterally negotiate exchanges of electrical energy surpluses over a discrete timeline to demonstrate that they can profit from learning to choose a negotiation strategy while selfishly accounting for contextual information under different circumstances in a data-driven way. Furthermore, several negotiation episodes are conducted in the proposed EIP between a context-aware agent and other types of agents proposed in the existing literature. Results obtained highlight that context-aware agents do not only reap selfishly higher benefits, but also promote social welfare as they resort to contextual information while learning to negotiate.     

Evolving Fuzzy Rules for Relaxed-Criteria Negotiation

In the literature on automated negotiation, very few negotiation agents are designed with the flexibility to slightly relax their negotiation criteria to reach a consensus more rapidly and with more certainty. Furthermore, these relaxed-criteria negotiation agents were not equipped with the ability to enhance their performance by learning and evolving their relaxed-criteria negotiation rules. The impetus of this work is designing market-driven negotiation agents (MDAs) that not only have the flexibility of relaxing bargaining criteria using fuzzy rules, but can also evolve their structures by learning new relaxed-criteria fuzzy rules to improve their negotiation outcomes as they participate in negotiations in more e-markets. To this end, an evolutionary algorithm for adapting and evolving relaxed-criteria fuzzy rules was developed. Implementing the idea in a testbed, two kinds of experiments for evaluating and comparing EvEMDAs (MDAs with relaxed-criteria rules that are evolved using the evolutionary algorithm) and EMDAs (MDAs with relaxed-criteria rules that are manually constructed) were carried out through stochastic simulations. Empirical results show that: 1) EvEMDAs generally outperformed EMDAs in different types of e-markets and 2) the negotiation outcomes of EvEMDAs generally improved as they negotiated in more e-markets.      

Design of a Multi–Unit Double Auction E–Market

We envision a future economy where e–markets will play an essential role as exchange hubs for commodities and services. Future e–markets should be designed to be robust to manipulation, flexible, and sufficiently efficient in facilitating exchanges. One of the most important aspects of designing an e–market is market mechanism design. A market mechanism defines the organization, information exchange process, trading procedure, and clearance rules of a market. If we view an e–market as a multi–agent system, the market mechanism also defines the structure and rules of the environment in which agents (buyers and sellers) play the market game. We design an e–market mechanism that is strategy–proof with respect to reservation price, weakly budget–balanced , and individually rational . Our mechanism also makes sellers unlikely to underreport the supply volume to drive up the market price. In addition, by bounding our market's efficiency loss, we provide fairly unrestrictive sufficient conditions for the efficiency of our mechanism to converge in a strong sense when (1) the number of agents who successfully trade is large, or (2) the number of agents, trading and not , is large. We implement our design using the RETSINA infrastructure, a multi–agent system development toolkit. This enables us to validate our analytically derived bounds by numerically testing our e–market.     

基于模糊约束规划的自动协商

给出了一个基于模糊约束规划模型的自动协商系统。建立了模糊约束规划模型并利用模糊模拟、神经网络和遗传算法给出了求解Pareto最优解的混合智能算法;协商过程中卖方智能体根据神经网络拟合的效用函数并运行混合智能体算法得到当前协商步的Pareto最优解,避免了对大型商品数据库的反复搜索,为系统推向实际应用奠定了基础;协商模型仿真实验表明了协商系统返回的解与实际调查得到的用户偏好相一致。     

基于GNP的多Agent人工股市模型

结合奥地利学派的经济思想，本文介绍了一种新的基于GNP算法的多Agent人工股市模型。该模型采用GNP算法来模拟交易个体的行为模式，进化他们的决策规则；同时在设计上强化Agent的异质性，并利用GA算法来优化模型参数。仿真结果表明，GNP-ASM模型表现出很好的统计性能，能够体现真实股市的一些基本特征。     

Management decision support using long-term market simulation

In recent years Agent-based Computational Economics (ACE) has become an increasingly important method in market simulation. After liberalization of many former governmental owned or controlled industries the used operations research models are not longer sufficient to simulate market behavior due to individual action and increasing competition. Agent-based simulation appears to be an alternative approach considering also individual behavior and competition. Some short-term simulation approaches have shown promising results for the simulation in the domain of electricity markets. Picking up the desire for a long-term oriented simulation, this paper presents a basic agent-based model considering the investment decision within long-term planning of electricity markets. Additionally, regulatory agents are introduced as a third side in the market simulation to represent governmental decisions. This results in the definition of three types of agents representing electricity generating companies, consumers and governmental instances.     

MTO型供应链的价格/交货期协商支持模型

针对MTO(make-to-order)供应链环境下制造商与供应商的多个订单的价格/交货期协商问题，基于供应链伙伴间关系是竞争性合作的特点，提出一种新的两阶段协商议程．在合作性协商阶段，中介者利用模拟退火算法帮助制造商和供应商寻找最小化供应链总成本的交货期预协议点；制造商和供应商在此基础上基于整合效用的思想调整价格议题的保留值和期望值．在竞争性协商阶段双方逐步让步，就价格达成协议．实验表明，该协商议程能够获得近似最优的社会福利，达成对协商人双赢的方案．该协商议程能够有效应用于供应链协调和B2B在线市场．