A Reputation–Oriented Reinforcement Learning Strategy for Agents in Electronic Marketplaces

In this paper, we propose a reputation–oriented reinforcement learning algorithm for buying and selling agents in electronic market environments. We take into account the fact that multiple selling agents may offer the same good with different qualities. In our approach, buying agents learn to avoid the risk of purchasing low–quality goods and to maximize their expected value of goods by dynamically maintaining sets of reputable sellers. Selling agents learn to maximize their expected profits by adjusting product prices and by optionally altering the quality of their goods. Modeling the reputation of sellers allows buying agents to focus on those sellers with whom a certain degree of trust has been established. We also include the ability for buying agents to optionally explore the marketplace in order to discover new reputable sellers. As detailed in the paper, we believe that our proposed strategy leads to improved satisfaction for buyers and sellers, reduced communication load, and robust systems. In addition, we present preliminary experimental results that confirm some potential advantages of the proposed algorithm, and outline planned future experimentation to continue the evaluation of the model.     

基于推荐的抗攻击电子商务信任模型

针对目前在线信誉系统面临的自我提升攻击、恶意诋毁攻击和漂白攻击三类常见的攻击,提出了一种基于推荐的集中式信任模型。该模型综合了用户间购买行为的相似度以及评价的时效性确定对某件商品的推荐信任值,同时结合基于自身交易经验的直接信任值,来获取对该商品的综合信任度。通过在真实交易数据中注入三类攻击进行仿真,实验结果证明,相对于现有的信誉管理模型,该模型能更好地抵御攻击,为消费者提供更准确的卖家和商品信誉值。     

METrust: A mutual evaluation-based trust model for P2P networks

It is necessary to construct an effective trust model to build trust relationship between peers in peer-to-peer (P2P) network and enhance the security and reliability of P2P systems. The current trust models only focus on the consumers evaluation to a transaction, which may be abused by malicious peers to exaggerate or slander the provider deliberately. In this paper, we propose a novel trust model based on mutual evaluation, called METrust, to suppress the peers malicious behavior, such as dishonest evaluation and strategic attack. METrust considers the factors including mutual evaluation, similarity risk, time window, incentive, and punishment mechanism. The trust value is composed of the direct trust value and the recommendation trust value. In order to inhibit dishonest evaluation, both participants should give evaluation information based on peers own experiences about the transaction while computing the direct trust value. In view of this, the mutual evaluation consistency factor and its time decay function are proposed. Besides, to reduce the risk of computing the recommendation trust based on the recommendations of friend peers, the similarity risk is introduced to measure the uncertainty of the similarity computing, while similarity is used to measure credibility. The experimental results show that METrust is effective, and it has advantages in the inhibition of the various malicious behaviors.     

Protecting buying agents in e-marketplaces by direct experience trust modelling

In this paper, we describe a framework for modelling the trustworthiness of sellers in the context of an electronic marketplace where multiple selling agents may offer the same good with different qualities and selling agents may alter the quality of their goods. We consider that there may be dishonest sellers in the market (for example, agents who offer goods with high quality and later offer the same goods with very low quality). In our approach, buying agents use a combination of reinforcement learning and trust modelling to enhance their knowledge about selling agents and hence their opportunities to purchase high value goods in the marketplace. This paper focuses on presenting the theoretical results demonstrating how the modelling of trust can protect buying agents from dishonest selling agents. The results show that our proposed buying agents will not be harmed infinitely by dishonest selling agents and therefore will not incur infinite loss, if they are cautious in setting their penalty factor. We also discuss the value of our particular model for trust, in contrast with related work and conclude with directions for future research.     

电子商务中信用值的计算方法的改进与研究

电子商务作为一种全新的商务运作模式,信任与信用问题一直都是其的核心问题.在传统的商务贸易中,买卖双方的信义由纸质合同来约束,但是在虚拟的电子商务交易中,这种方式显然是不可行的。因此就需要一套合理的信任与信用评价机制来给卖家的信用进行量化,方便买家的选择。由于现有的信任模型都过于简单,无法完整反应信任主体的信任风险,因此以淘宝网为例,本文提出在电子商务中把商品的价格因素也作为计算因子参与到信任与信用的量化中,并证明了这个问题是多项式时间可解的。     

电子商务下的信任网络构造与优化

电子商务环境中交易实体间的信任关系类似于传统商务环境中复杂的社会关系.实体间的信任度量涉及到交易额、交易发生时间、消费实体个人收入及其对信任的风险态度等因素,难以准确地给出量化计算.为探明这种信任关系的本质特点,结合现实生活中社会关系网络的一些认知理论和方法,详细分析和定义了实体及实体关系的相关属性,提出了一种信任网络描述的形式化模型.研究了信任网络的构造方法,建立了一套信任网络优化算法,有效地降低了信任网络的复杂性.最后,给出了一套信任网络可视化自动生成工具,通过实例应用分析表明,信任网络形式化描述模型和优化算法可以很好地揭示电子商务环境中复杂的信任关系,降低了信任度量算法的复杂度,可为信任的传播机制和信任计算模型的研究提供理论基础.     

E-commerce trust metrics and models

Traditional models of trust between vendors and buyers fall short of requirements for an electronic marketplace, where anonymous transactions cross territorial and legal boundaries as well as traditional value-chain structures. Alternative quantifications of trust may offer better evaluations of transaction risk in this environment. This article introduces a notion of quantifiable trust and then develops models that can use these metrics to verify e-commerce transactions in ways that might be able to satisfy the requirements of mutual trust. The article uses two examples in illustrating these concepts: one for an e-commerce printing enterprise and the other for Internet stock trading     

Trusted P2P transactions with fuzzy reputation aggregation

Internet commerce and online commodity exchanges suffer from distrust among sellers and buyers, who are often strangers to each other. The authors present a new P2P reputation system based on fuzzy logic inferences, which can better handle uncertainty, fuzziness, and incomplete information in peer trust reports. This system aggregates peer reputations with affordable message overhead. By testing the system using eBay transaction data in the public domain, the authors seek to demonstrate the efficacy and robustness of two P2P reputation systems - fuzzytrust and eigentrust - at establishing trust among the peers in P2P applications.     

C2C商家信任度动态分类机制研究

在C2C电子商务的交易中,买家因交易目的不同,对商家信任度的粒度要求是不同的。为提高交易的成功率,应建立商家信任度的动态分类机制,以满足不同应用的需求。为此,从买家对商家信任的本质出发,首先通过使用模糊集合理论的隶属度概念,提出了信任的定量描述方法;其次,引进模糊聚类分析方法,建立了商家信任度的动态分类机制;最后,通过实验仿真分析,验证了该方法的有效性和合理性。     

一种基于模糊理论的P2P电子商务信任模型

为了提高P2P电子商务交易的安全性,根据P2P电子商务的特征,提出一种基于模糊理论的信任模型。将信任化分为直接信任和推荐信任。用模糊集来刻画直接信任值,对影响信任主体的多种因素给出了详细的模糊综合评判算法。利用交易金额和交易时间来确定推荐信任的权值。实验表明该信任模型与基于概率估计的信誉评价体系算法相比,该算法误差较小,能有效防止节点的恶意行为,可以很好地应用于P2P电子商务中。     

To sell or not to sell: Exploring sellers' trust and risk of chargeback fraud in cross‐border electronic commerce

Over the past few decades, chargeback fraud from buyers has been identified as a major risk faced by online sellers, particularly small‐ and medium‐sized enterprises, in cross‐border electronic commerce. However, most previous studies have focused on trust and perceived risk from the buyers' perspective and in domestic online marketplaces, while neglecting the importance of sellers' trust and perceived risk in the success of online transactions and the significance of cross‐border transactions. To fill this gap in the literature, this study examines both the antecedents and the impacts of sellers' trust in buyers and their perceived risk of chargeback fraud on sellers' intention to trade with buyers in the context of cross‐border e‐commerce. To this end, we develop a conceptual model that identifies a set of institutional mechanisms to enhance sellers' trust and reduce their perceived risk. Hypotheses are tested via a survey of 443 sellers on DHgate.com , one of the major cross‐border e‐commerce websites connecting the small‐ and medium‐sized enterprises of mainland China with overseas buyers. Our research makes concrete contributions to e‐commerce research and generates useful insights for third‐party online transaction platforms and online trade policy makers.     

Trust-oriented buyer strategies for seller reporting and selection in competitive electronic marketplaces

In competitive electronic marketplaces where some selling agents may be dishonest and quality products offered by good sellers are limited, selecting the most profitable sellers as transaction partners is challenging, especially when buying agents lack personal experience with sellers. Reputation systems help buyers to select sellers by aggregating seller information reported by other buyers (called advisers). However, in such competitive marketplaces, buyers may also be concerned about the possibility of losing business opportunities with good sellers if they report truthful seller information. In this paper, we propose a trust-oriented mechanism built on a game theoretic basis for buyers to: (1) determine an optimal seller reporting strategy, by modeling the trustworthiness (competency and willingness) of advisers in reporting seller information; (2) discover sellers who maximize their profit by modeling the trustworthiness of sellers and considering the buyers’ preferences on product quality. Experimental results confirm that competitive marketplaces operating with our mechanism lead to better profit for buyers and create incentives for seller honesty.     

基于群组的C2C电子商务信任模型研究

国内的电子商务平台大多采用eBay信任模型,对买家反馈评分进行简单累加得到卖家信誉值,未区分买家反馈评分的合理性及其参考价值的重要程度。为此,提出一种基于群组的C2C电子商务信任模型,通过计算买家与卖家的熟悉度,确定买家的可信度,综合考虑反馈评分、交易次数、交易价格、交易时间、以往买家的可信度对信誉的影响,构建电子商务信任模型。模拟实验结果证明,相比Sporas模型,该模型能为买家提供更全面、更准确的卖家信誉信息。     

一种直接评价节点诚信度的分布式信任机制

基于信誉的信任机制能够有效解决P2P网络中病毒泛滥和欺诈行为等问题.现有信任机制大多采用单个信誉值描述节点的诚信度,不能防止恶意节点用诚信买行为掩盖恶意卖行为;而且从信誉值上无法区分初始节点和恶意节点.提出一种新的分布式信任机制,基于交易历史,通过迭代求解,为每个节点计算全局买信誉值和卖信誉值,根据信誉值便能判断节点的善恶.仿真实验对比和性能分析表明,与EigenTrust算法相比,该算法能够迅速降低恶意节点的全局信誉值,抑制合谋攻击,降低恶意交易概率.     

Filtering unfair ratings from dishonest advisors in multi-criteria e-markets: a biclustering-based approach

In multiagent e-markets, trust between interaction partners (buying agents and selling agents) is vital for any transaction to be successful. Given the difficulty for a buyer to directly judge the quality (trustworthiness) of a seller for a transaction, a buyer also seeks opinions from other buyers (called advisors) in the marketplace to determine the seller’s trustworthiness. However, advisors may act dishonestly by conveying misleading information about the seller. We propose a novel approach to identify such dishonest advisors, while evaluating a seller’s trustworthiness on multiple criteria. It is based on a biclustering method which clusters honest advisors on different criteria. Correlation between advisors’ ratings to various criteria is used as additional information to accurately filter dishonest advisors. A transitive mechanism is also employed in the biclustering process to cope with rating sparsity. Further, we introduce a parallelization technique to reduce the time complexity involved in the biclustering process. Detailed experiments in simulated environments demonstrate the robustness of the proposed approach against strategic attacks from dishonest advisors. Evaluation on three real datasets confirms the effectiveness of our approach in real environments.     

基于交易特征和反馈评价的P2P信任模型

提出了一种新的在P2P系统中基于交易特征和反馈评价的信任评估机制。为确定反馈评价的真实性,模型引入了时间衰减函数和事务影响参数,给出了反馈评价的可信度计算方法。实验仿真结果表明,该评估机制能够提高局部声誉和全局声誉的计算准确性,有效地抑制恶意节点。与信任模型PeerTrust和EigenTrust相比,该模型的性能优于其他两者,能够更好地应用于P2P电子商务系统中。     

基于评价向量的P2P电子商务信任模型

针对现有P2P信任模型中交易因素考虑不全面、缺乏恶意节点识别机制而导致无法防御恶意节点共谋攻击和耗费网络带宽等问题,提出一种新的P2P信任模型EVTM,该模型采用向量化的方式表示评价的标准,引入时间衰减因子和惩罚机制,促使模型中交易节点积极地、正确地评价,从而构造一个诚信、可靠的交易环境。仿真实验进一步证明EVTM不仅可以根据用户的不同需求对交易对象做出更合理的信任评估,而且能有效地避免恶意节点的共谋攻击,从而降低交易的风险,减少损失。     

一种基于二层节点和客观风险的电子商务交易信任模型

为解决P2P环境下电子商务的安全交易问题,在深入研究电子商务相关信任模型的基础上,基于交易中可能存在的客观风险,提出了一种基于二层节点的综合信任度的计算模型。综合考虑了影响交易的交易金额、交易时间等多种因素,引入了可交易度的概念,并将其作为节点是否进行交易的决策依据。实验表明,该模型能够更准确地计算节点的信任值,可有效地提高交易的安全性。     

DWATrust:一种基于“二次加权法”的P2P网络动态综合信任模型

针对现有的P2P网络信任模型在聚合节点信任值时对节点行为的差异性与动态性考虑不足,提出了一种基于“二次加权法的”的P2P网络动态综合信任模型—DWATrust。该模型在对节点进行评价时,首先通过引入“时序立体数据表”来记录节点在过去某几段时间内不同评价指标下的评价得分,然后通过“嫡值法”分别计算出各个时间段内各个节点对于各个评价指标的不同权值并进行第一次加权综合,得到各个节点在不同时间段内的综合信任值。最后,通过求解一个“非线性规划问题”计算出各个时间段的权值并进行第二次加权综合,得到各个节点在整个时间段上的综合信任值。由此可见,该模型不仅充分考虑到交易上下文及节点上下文的动态变化对节点信任值的影响,而且引入时间粒度来反映这种变化。仿真实验表明,该模型可以较好地识别节点进行周期性振荡欺骗等恶意行为,从而大大改善P2P网络的交易成功率。     

一种基于差评散布的P2P网络信任机制

面对各种网络攻击,P2P网络需要有效的信任机制隔离恶意节点,保证节点的成功交易。考虑节点行为特征和差评的重要性,提出基于差评散布的信任机制。服务节点一旦提供的服务被给出差评,对其近期交易的相关节点进行差评的散布,加大差评对服务节点声誉的影响力度。经过二次计算的节点声誉值能真实反映节点近期的声誉水平与交易趋势。实验结果表明,该信任机制能保证正常节点的交易成功率,有效对抗各种攻击行为。