Bidding agents for online auctions with hidden bids

There is much active research into the design of automated bidding agents, particularly for environments that involve multiple decoupled auctions. These settings are complex partly because an agent’s strategy depends on information about other bidders’interests. When bidders’ valuation distributions are not known ex ante, machine learning techniques can be used to approximate them from historical data. It is a characteristic feature of auctions, however, that information about some bidders’valuations is systematically concealed. This occurs in the sense that some bidders may fail to bid at all because the asking price exceeds their valuations, and also in the sense that a high bidder may not be compelled to reveal her valuation. Ignoring these “hidden bids” can introduce bias into the estimation of valuation distributions. To overcome this problem, we propose an EM-based algorithm. We validate the algorithm experimentally using agents that react to their environments both decision-theoretically and game-theoretically, using both synthetic and real-world (eBay) datasets. We show that our approach estimates bidders’ valuation distributions and the distribution over the true number of bidders significantly more accurately than more straightforward density estimation techniques. Editors: Amy Greenwald and Michael Littman An earlier version of this work was presented at the Workshop on Game-Theoretic and Decision-Theoretic Agents (GTDT) 2005, Edinburgh, Scotland.     

An interactive approach for multi-attribute auctions

Auction processes are commonly employed in many environments. With rapid advances in Internet and computing technologies, electronic auctions have become very popular. People sell and buy a wide range of goods and services online. There is a growing need for the proper management of online auctions and for providing support to parties involved. In this paper, we develop an interactive approach supporting both the buyer and the bidders in a multi-attribute, single-item, multi-round, reverse auction environment. We demonstrate the algorithm on a number of problems.     

Bidding strategies for real-life small loan auctions

We define and identify bidding strategies in real-life small loan auctions (Prosper.com). In such auctions, lenders bid for borrowers' loan listings and the winners get to fund the loan at an interest rate determined by the auction. The exceptionally large empirical database provided by Prosper.com offers a unique opportunity to test and further develop the theory of online auctions. This study shows that bidding behavior is not homogeneous among bidders, as the traditional auction theory suggests. Instead, bidders use many different bidding strategies. Moreover, learning and bidders' consistency over time in different auctions is studied.     

Online auctions enabling the secondary computer market

The Internet is enabling new forms of commerce and novel markets. One example is the secondary computer market, facilitating exchange between quality sensitive sellers, oftentimes businesses, and price sensitive buyers. As this market does not have a viable physical counterpart with reference prices, it is developing via online auctions. One question of interest in the evolution of this market is the determinants of prices. Using a dataset of 2,000 laptop auctions in a seven-month period, this research provides support for accepted auction theory while raising questions that deserve further explanation. The negative relationship between supply and auction price supports standard supply and demand theory, while higher prices for better features is consistent with vertical differentiation. Even within accepted theory this research broadens the understanding of auction behavior. There is clear support for the “price decline anomaly” where prices in sequential auctions decline, violating the “law of one price.” One result that deserves further attention is that midweek auctions realize higher prices. A second is that price changes over time are not monotonic. Future research should replicate and explain these results, as well as extend them to other auction settings. As the secondary computer market evolves it will impact the primary computer market.     

Ascent EM for fast and global solutions to finite mixtures: An application to curve-clustering of online auctions

In this paper we propose two new EM-type algorithms for model-based clustering. The first algorithm, Ascent EM, draws its ideas from the Monte Carlo EM algorithm and uses only random subsets from the entire database. Using only a subset rather than the entire database allows for significant computational improvements since many fewer data points need to be evaluated in every iteration. We also argue that one can choose the subsets intelligently by appealing to EMs highly-appreciated likelihood-ascent property. The second algorithm that we propose builds upon Ascent EM and incorporates ideas from evolutionary computation to find the global optimum. Model-based clustering can feature local, sub-optimal solutions which can make it hard to find the global optimum. Our algorithm borrows ideas from the Genetic Algorithm (GA) by incorporating the concepts of crossover, mutation and selection into EMs updating scheme. We call this new algorithm the GA Ascent EM algorithm. We investigate the performance of these two algorithms in a functional database of online auction price-curves gathered from eBay.com.     

Design of online auctions: Proxy versus non-proxy settings

Recent years have witnessed the rapid development of online auctions. Currently, some online auctions, such as eBay, introduce a proxy bidding policy, under which bidders submit their maximum bids and delegate to a proxy agent to automatically outbid other competitors for the top bidder, whereas other online auctions do not. This paper compares these two widely used auction mechanisms (proxy setting and non-proxy setting) and characterizes the equilibrium bidding behavior and the seller's expected revenue. We find the proxy auction outperforms the non-proxy auction in terms of the seller's expected revenue. This dominance result is not prone to the specific bid announcement policy, the bidder's knowledge regarding the number of bidders, the impact of traffic congestion along the bidding process, the number of items sold through the auction, and the existence of a reserve price.We further find that the proxy setting usually fails to sustain the truthful bidding as a dominant strategy equilibrium even if no minimum bid increments are adopted, and the possibility of a low-valuation-bidder dilemma where the low-valuation bidders could be better off if all bidders collude to bid at the last minute. We also discuss the dramatically different equilibrium bidding behaviors under the two auction mechanisms.     

The appropriate role of dispute resolution in building trust online

This article examines the relationship between online dispute resolution (ODR) and trust. We discuss what trust is, why trust is important, and how trust develops. Our claim is that efforts to implement online dispute resolution on a site or service in a manner that promotes trust need to consider ODR as just one tool in a broader toolbox of trust-building tools and techniques. These techniques are amongst others marketing, education, trust seals, and transparency. By evaluating ODR in its proper context as one component of a larger trust strategy, we can more accurately set expectations for its results and position our projects for success.“Trust in Allah, but tie your camel” – Muslim Proverb     

Bidding strategies in online single-unit auctions: Their impact and satisfaction

Online bidders use different strategies in their biddings. However, we are unsure of the bidders strategies and their effectiveness in achieving auction goals. Our study was an attempt to identify bidding strategies empirically in online single-unit auctions and evaluate their outcome in terms of cost saving, perceived bidder enjoyment, and bidder satisfaction. A research model was developed and used to examine the relationships. Both objective and subjective data of online single-unit auctions were collected from Taobao.com to validate our postulated hypotheses. We found three main bidding strategies: early, snipe, and agent-supported ratchet bidding based on their behavior patterns. These resulted in different levels of winning outcome and cost saving, but had no significant effect on perceived enjoyment. The hypotheses of the relationship between auction outcomes and bidder satisfaction of their bidding strategies were confirmed.     

The influence of equivocality in purchasing tasks on the selection of transaction channels in online auctions

Online auctions are one of the most active business models used in electronic commerce. Previous researchers address issues of online auction behaviour focusing on the factors influencing bidding intentions, but how bidders choose transaction channels to complete the consumption process is not examined before. This study conducts an experiment to manipulate the equivocality of purchasing task. Results show that when purchasing a product with higher task equivocality, bidders tend to choose a communication channel with higher information richness, and select a payment and product delivery channel with lower risk. When purchasing a product with lower task equivocality, bidders tend to select a communication channel with lower information richness, and tolerate higher risk to complete the payment and product delivery process.     

Analysis of fraudulent behavior strategies in online auctions for detecting latent fraudsters

Online auction fraudsters constantly monitor the contextual situations of the auction and change their behavior strategies accordingly to distract the attention of their targets. This flipping of behavior makes it difficult to identify fraudsters. Thus, legitimate traders need appropriate countermeasures to avoid becoming victimized. To help online auction users detect fraudsters as early as possible, this study develops a systematic method to discover the fraudulent strategies from proven cases of online auction fraud. First, according to the results of cluster analysis on the proven fraudsters, four typical types of fraud are identified, which are Aggressive, Classical, Luxury and Low-profiled. To provide better insight, a strategy is further represented by a series of status transitions. Hidden statuses of latent fraudsters are discovered by applying X-means clustering to the phased profiles of their transaction histories. As a result, various strategies can be extracted by such a systematic method and interesting characteristics are found in these strategies. For example, about 80% fraudsters in the Yahoo!Taiwan auction site flip their behavior no more than two times, which is not as complicated as expected originally. Based on these discovered fraudulent statuses, a high-resolution fraud detection method is performed to classify suspects into legitimate users or fraudsters in different statuses, potentially improving overall detection accuracy. A two-way monitoring procedure is then proposed to successively examine the statuses of a suspicious account. Analysis shows that the two-way monitoring method is promising for better detection of well-camouflaged fraudsters.     

Social interaction and continuance intention in online auctions: A social capital perspective

This study explores how interaction within an online auction community affects online auction actor intention to continue trading with others. Adopting a social perspective drawing on social capital theory and IS literature, this study investigates how interactions among actors contribute to the creation and advancement of social capital. The analytical results demonstrate that the influence of user interaction on continuance intention in online auctions is mediated by the creation of various dimensions of social capital at the community level. Finally, the implications of the study findings are discussed.     

在线信誉系统中的信任模型构建研究

针对现有在线信誉系统中信任模型的缺陷,基于在线拍卖的特点,并结合已有信任研究成果,构建了基于多影响因素的信任模型．本模型适用于在线拍卖环境下对用户信誉状况的全面、准确的评估．仿真实验表明,与现有信任模型相比,本模型的信任度计算精确度较高,具有较好的可行性．     

Real-time detection of shill bidding in online auctions: A literature review

Online auctions have become an increasingly popular and convenient way for conducting ecommerce transactions on the Web. However, the rapid surge of users participating in online auctions has led to auction fraud. Among the types of auction fraud, the most prominent is Shill bidding. Shill bidding is intentionally fake bidding by a seller on his/her own auction to inflate the final price. This can be accomplished either by the seller himself/herself or by someone colluding with the seller to place fake bids on his/her behalf. Therefore, it is difficult to manually investigate the large amount of auctions and bidders for shill bidding activities. Detecting shill bidding in real-time is the most effective way to reduce the loss result of the auction fraud. Researchers have proposed multiple approaches and experimented to control the losses incurred due to shill bidding. This paper investigates the real-time detection techniques of shill bidding. It also provides a brief overview of major work that has been conducted in shill bidding detection including both offline and real-time approaches. Furthermore, this paper identifies research gaps in the detection and prevention of shill bidding behaviours. It also provides future research issues and challenges to detect shill bidding in real-time.     

Design, development and validation of an agent-based model of electronic auctions

This paper presents the design, development and validation methodology of an agent-based computational model of the B2C electronic auction marketplace. It aims at a comprehensive understanding of the varied issues governing a B2C electronic auction, incorporating the behavior of all relevant agents such as the auctioneer, the consumer and the retailer; and the environment in which these agents operate and interact. In contrast with conventional methods, agent based modeling employs a bottom-up modeling approach where behaviors of individual agents and rules for their interaction, specified at the micro level, give rise to emergent macro level phenomenon. The development methodology should ensure that agent models are aligned with theory, current knowledge of the field and observed phenomena, and output validity of the model also needs to be ascertained. Beginning with a general introduction to agent based computational modeling, this paper formalizes this alignment and validation methodology and elaborates each step, noting the rationale and means for achieving these. The manner in which this process was used in modeling B2C auctions is then described.     

An empirical test to measure the effectiveness of online advertising in online marketplaces using a hierarchical Bayes model

Online marketplace, taken the form of “open market” where a very large number of buyers and sellers participate, has occupied a rapid increasing position in e-commerce, which resulting in sellers’ increasing investment on online advertising. Hence, there is a growing need to identify the effectiveness of online advertising in the online marketplaces such as eBay.com. However, it is problematic to directly apply the existing online advertising effect models for click-through data of online marketplaces. Therefore, there is a need for developing a model to estimate the effectiveness of online advertising in online marketplace considering its characteristics. In this paper, we develop an analytical Bayesian approach to modeling click-though data by employing the Poisson-gamma distribution. Our results have implications for online advertising effect measurement, and may help guide advertisers in decision-making.     

Doing their bidding: An empirical examination of factors that affect a buyer’s utility in Internet auctions

What factors make individual bidders pay more or less for the same item in online auctions? We use data on over 55,000 bids over a three-year period collected by a customized Internet software agent. These data are used to perform a within-bidders quasi-experiment, testing bidders who bid on the exact same item at different times during a 30-day period in online auctions. With theories from information systems and consumer behavior as our theoretical lens, we then examine factors that make individuals pay more for the exact same item in online auctions. We find that the same individual will tend to pay more for items sold on a weekend, for items with a picture, and for items sold by experienced sellers. We also find that the same individual is willing to pay more for the same item if others express an interest in that item, exhibiting a type of herd effect. Our results are generalizable to other auctions, and shed light on electronic commerce sales in general, where firms try to sell products for the highest possible price.     

基于改进在线支持向量回归的离子浓度预测模型

针对湿法炼锌净化过程中杂质离子浓度检测的大滞后特性和模型失效问题.提出了基于在线支持向量回归的离子浓度预测模型.该模型对每个新样本进行增量学习,并能删除数据集中的一个旧样本.进而提出用分块矩阵的方法解决更新算法计算复杂的问题.将该建模方法应用于离子浓度的预测,结果表明预测模型具有较好的泛化性能,模型更新时间明显缩短,有效地提高了适应工况的实时性.     

基于网上逆向拍卖的供应链绩效研究

长期以来,拍卖是一种非常流行的获得产品和服务的方法,本文在供应链环境下研究网上逆向拍卖,通过两个拍卖模型,比较得出这样的结论：在供应链环境下,如果同时考虑生产成本和运输成本,网上拍卖可以较大的降低供应链总成本,而且只会引起供应链上企业成本的小幅上涨。     

A multi-agent approach to Intelligent Transportation Systems modeling with combinatorial auctions

Challenges of urbanization require new, more flexible approaches to design of public transportation systems. Demand Responsive Transport systems (DRT) that provide a share transportation services with flexible routes and focus on optimizing of economic and environmental value are becoming an important part of public transportation. In this paper we propose a new approach to design of DRT models which considers DRT as a multi-agent system (MAS) where various autonomous agents represent interests of system’s stakeholders. The distributed nature of the MAS facilitates design of scalable implementations in modern cloud environments. We also propose a planning algorithm based on combinatorial auctions (CA) that allows to express commodity of multiple transportation scenarios by evident means of the bids. Using the mechanism of CA we may fully take into account the presence of complementariness and substitutability among the items that differ across bidders. Further, we describe design principles of our proposed software with a prototype implementation. We believe that our approach to multi-agent modeling is general enough to provide the flexibility necessary for adoption of DRT-services modeling into real-world scenarios. The results of modeling have been compared against several cases of a local bus provider and validated in a set of computational experiments.