基于用户的Web服务FRC评估选择模型

Web服务非功能属性评佑是服务选择的重要前提,而目前的服务评佑方法没有根据各非功能属性内在特征进行其属性值的评估,也没有考虑用户对多个属性的复杂需求,无法有效地选择出真正满足用户需求的最佳服务。因此从用户角度出发,提出了基于用户的Web服务FRC评佑选择模型,模型考虑了用户对各个属性的需求,并根据非功能属性隶属的不同数学性质,将隶属度的概念、模糊评判理论、概率统计方法和TOPSIS多属性决策法应用于模型,建立了模糊性子模型F和随机性子模型R,最终通过确定性子模型C综合评估来实现服务选择。仿真实验结果表明,该模型能较好地根据用户需求有效实现服务选择。     

Estimation of Bid Functions for Location Choice and Price Modeling with a Latent Variable Approach

A new approach for the estimation of bid-rent functions for residential location choice is proposed. The method is based on the bid-auction approach and considers that the expected maximum bid of the auction is a latent variable that can be related to observed price indicators through a measurement equation. The method has the advantage of allowing for the estimation of the parameters of the bid function that explain the heterogeneous preferences of households for location while simultaneously adjusting the expected maximum bid to reproduce realistic values. The model is applied and validated for a case study on the city of Brussels. Results show that the proposed model outperforms other methods for bid-rent estimation, both in terms of real estate prices and spatial distribution of agents, especially when detailed data describing the real estate goods and their prices is not available.     

Functional modelling of volatility in the Swedish limit order book

The publicly available electronic limit order book at the Stockholm Stock Exchange consists of five levels of prices and quantities of a given stock with a bid and ask side. All changes in the book during one day can be recorded with a time quote. Studying the variation of the quoted price returns as a function of quantity is discussed. In particular, discovering and modelling dynamic behaviours in the volatility of prices and liquidity measures are considered. Applying a functional approach, estimation of the volatility dynamics of the spreads, created as differences between the ask and bid prices, is presented through a case study. For that purpose two-step estimation of functional linear models is used, extending this method to a time series context.     

满足工作流执行时限的可抢占虚拟机实例配置和调度方法研究

随着云计算的迅速发展,将工作流部署到云计算平台已经成为了常见的选择。相比于传统的本地工作流,云工作流不仅要考虑计算时长等要求,还要考虑其产生的经济开销。而云计算服务商为了提高资源利用率,提供了可抢占虚拟机实例这种非常廉价但是不稳定的资源。针对工作流在云计算中的调度和执行问题,提出一种满足工作流执行时限的可抢占虚拟机实例配置和调度方法。该方法使用马尔科夫模型和动态规划方法,对可抢占虚拟机实例的价格进行预测,并得到成本最低的出价策略。同时,结合工作流的执行时限要求,在估计的出价策略下对工作流中使用的实例进行配置。实验结果显示,相比于全部使用按需付费虚拟机实例,该方法在满足工作流执行时限的前提下最高可以节省89.9%的计算成本。     

基于文本分析的标书综合评估模型

人工智能的发展为传统的标书评估方法的优化和改进提供了新的方法, 针对标书评估中人工评标效率低和难以有效识别围标、串标行为的问题, 本文提出了一种基于文本分析的标书综合评估模型, 包含文本评估模型和文本评级模型, 模型为更客观、科学、智能化地进行工程建设项目的评标和防范围标、串标提供支持. 首先, 构建文本评估模型, 在传统的评标指标中加入基于Shingling算法计算的投标文件的重复率, 并将投标文件要求的模板目录与真实目录进行匹配对比计算投标文件的响应程度, 利用层次分析法计算文本评估指标的权重. 然后, 构建文本评级模型, 基于权重改进的Simhash算法计算投标文件相似度, 采用企业关联度、资质与报价的一致性、价格上(下)浮率、企业关联度、异常行为等评级指标, 通过综合评级获得投标文件的评级结果, 协助评标专家识别围标、串标行为. 最后, 通过文本评估模型定量计算得到标书得分排序, 通过文本评级模型定性分析得到标书识别围标、串标的结果, 两者共同实现了对标书的综合评估.     

Online evaluation of bid prediction models in a large-scale computational advertising platform: decision making and insights

Online media provides opportunities for marketers through which they can deliver effective brand messages to a wide range of audiences at scale. Advertising technology platforms enable advertisers to reach their target audience by delivering ad impressions to online users in real time. In order to identify the best marketing message for a user and to purchase impressions at the right price, we rely heavily on bid prediction and optimization models. Even though the bid prediction models are well studied in the literature, the equally important subject of model evaluation is usually overlooked or not discussed in detail. Effective and reliable evaluation of an online bidding model is crucial for making faster model improvements as well as for utilizing the marketing budgets more efficiently. In this paper, we present an experimentation framework for bid prediction models where our focus is on the practical aspects of model evaluation. Specifically, we outline the unique challenges we encounter in our platform due to a variety of factors such as heterogeneous goal definitions, varying budget requirements across different campaigns, high seasonality and the auction-based environment for inventory purchasing. Then, we introduce return on investment as a unified model performance (i.e., success) metric and explain its merits over more traditional metrics such as click-through rate or conversion rate. Most importantly, we discuss commonly used evaluation and metric summarization approaches in detail and propose a more accurate method for online evaluation of new experimental models against the baseline. Our meta-analysis-based approach addresses various shortcomings of other methods and yields statistically robust conclusions that allow us to conclude experiments more quickly in a reliable manner. We demonstrate the effectiveness of our evaluation strategy on real campaign data through some experiments.     

Combinatorial auction under fuzzy environment

Combinatorial auction (CA) mechanism allows bundling of multiple items in packages, which can be solved through a clearing method termed as the winner determination problem (WDP). However, to date, there has yet to be a CA model that accounts for the fuzziness of bidders’ submitted prices. The imprecision in submitted prices is the result of the time gap between bid placement and winning bid announcement, which reflects the bidders’ expected values of the goods at the point of contract sale. Despite this common understanding, conventional CA modeling still treats the prices as deterministic. This causes a major shortcoming when an uncertain environment is assumed to be deterministic and solved through conventional WDP. This study shows that a fuzzy environment modeled via a deterministic WDP approach provides overly optimistic revenue for the auctioneer. A method of using possibilistic distributions of submitted prices to account for price uncertainty is proposed and formalized as Fuzzy Combinatorial Auction Winner Determination Problem (Fuzzy CA WDP). The difference in optimal solutions in deterministic WDP and fuzzy WDP reflects the amount of over estimation when a fuzzy situation is treated as though it is precise. It also reflects the information value when the uncertainty inherent in the fuzzy environment is resolved. Given that the information value is quantified in unit dollars, the fuzzy WDP approach allows the auctioneer to estimate its “true” revenue despite price uncertainties.     

招标采购大数据分析中的合理价格区间预测方案研究

公司在发展战略中时常会提出提升物资管理水平的任务,优化采购策略,提高物资采购的档次以及质量。然而市场环境错综复杂,涉及的变量因素人为难以把握。对于企业来说,招标采购过程中不合理中标现象的影响和危害巨大。因此事先把握合理中标价的区间值至关重要。预测合理价格区间,本文分为两个步骤：首先通过对以往所有同类招标过程数据的训练得出一个SVM模型,再依据本次招标的投标价适应模型估算出一个合理中标值。因为能采用的特征值较少,对SVM调参不能解决优化的问题。如何求取合理中标值左右两端的合理偏差值,本文比较了两种方法,第一种是将大量同类数据的预测结果与实际值对比,去噪后将最大值作为合理偏差值;第二种则利用假设性检验原则验证在合理中标值左右存在的投标个数百分比,中标价往往在这个偏移范围内。第二种方法很好地解决了投标价差距较大的情况,在假设历史中标价格均为合理中标价格的前提下,准确度能达到90%以上,并确保结果具有相当的参考价值,证明利用学习算法预测合理中标价具有较高可行性。     

A Dimension Reduction Shannon-Wavelet Based Method for Option Pricing

We present a robust and highly efficient dimension reduction Shannon-wavelet method for computing European option prices and hedging parameters under a general jump-diffusion model with square-root stochastic variance and multi-factor Gaussian interest rates. Within a dimension reduction framework, the option price can be expressed as a two-dimensional integral that involves only (i) the value of the variance at the terminal time, and (ii) the time-integrated variance process conditional on this value. A Shannon wavelet inverse Fourier technique is developed to approximate the conditional density of the time-integrated variance process. Furthermore, thanks to the excellent approximation properties of Shannon wavelets, the overall pricing procedure is reduced to the evaluation of just a single integral that involves only the density of the terminal variance value. This single integral can be accurately evaluated, since the density of the variance at the terminal time is known in closed-form. We develop sharp approximation error bounds for the option price and hedging parameters. Numerical experiments confirm the robustness and impressive efficiency of the method.     

Implications of a Reserve Price in an Agent-Based Common-Value Auction

Auction sellers can use a reserve price to require a minimum bid before items are sold. Theoretical and experimental research has tested the influence of a reserve price in an independent private values auction, but little focus has been given to the influence of a reserve price in a first-price common-value auction. We establish an agent-based first-price common-value auction to determine the impact of the reserve price with two buyers and with three buyers. An agent-based approach to this problem is both a unique contribution to the literature and appropriate since finding analytical solutions with common-value auctions is difficult. The agent-based model approach also allows us to consider buyers that have non-symmetric bid functions. Furthermore, we introduce a combination of numerical integration techniques with a new particle swarm learning algorithm. The buyers in the model choose their expected-net-revenue-maximizing bid price, and sellers choose their expected-revenue-maximizing reserve price. In the two-buyer and three-buyer auction, a reserve price increases the equilibrium winning bid price, decreases the probability that the item is sold, and increases the seller’s expected revenue. A reserve price in a two-buyer auction increases the winning bid price more than including an additional buyer in the auction with no reserve price. However, due to only receiving a salvage value when the item does not sell in the auction, the seller’s expected revenue is higher in the three-buyer first-price common-value auction without a reserve price than in the two-buyer auction with a reserve price.     

基于拍卖博弈的电子商务自动协商

为提高电子商务自动协商系统效率,本文以拍卖博弈理论为基础,提出并实现了一种基于拍卖博弈的自动协商Agent模型,并在此基础上实现了一个基于拍卖博弈的电子商务自动协商原型系统,应用于一个企业敏捷供应链管理系统中实现自动协商交易。     

不确定环境下的岸桥集卡协调调度耦合模型建立与求解

集装箱码头系统是一个由多个子系统组成的复杂的生产系统,系统内资源的调度也是非线性的复杂问题,同时涉及多种多样的不确定性因素。从不确定性的角度出发,主要考虑码头装卸设备运行参数的概率分布,研究岸桥和集卡之间的协调调度问题。采用多学科变量耦合优化设计的方法,同时考虑了集装箱任务的时间窗约束,分别建立集卡分派子模型和集卡配置子模型。并将完工时刻和集卡数量作为公用设计变量连接两个子模型,建立了协调调度耦合模型。选取上海港某码头的数据编写算例,在Visual Studio 2012环境下调用Gurobi4.0求解该耦合模型,反复迭代计算后得出最优的集卡分派方案相对于最初的调度方案,总延误时间成本下降了90.69%,集卡数量下降了30.76%,验证了本模型的有效性和实用性。     

Bid evaluation behavior in online procurement auctions involving technical and business experts

Multi-attribute reverse auction-based procurement has been widely used by large organizations. The attributes of the auctioned objects are usually divided into two groups: technical and business attributes. They are reviewed and scored by technical and business experts who act as referees in the bid evaluation process. To analyze their bid evaluation behavior, we built a model for a multi-attribute reverse auction. With correlations between the bid evaluations of the different referee groups across the attributes, the bid evaluation problem is not the usual multi-attribute decision-making problem. We assess the cause–effect relationship that is present, and show that antagonism between referee groups tends to grow over time. We tested how this works with data from simulated auctions. To diminish the potential for antagonism between the two referee groups, we propose a modified bid evaluation mechanism. We also conducted role-playing experiments involving the referee behaviors as a means for assessing the proposed mechanism. Our results suggest that the modified bid evaluation mechanism is beneficial.     

基于粗糙集与BP神经网络的多因素预测模型

运用粗糙集方法和信息熵概念,在不改变训练样本分类质量的条件下,按照输入影响因素相对于输出的重要度的大小,对输入参数集进行约简,确定神经网络输入层变量和神经元个数。通过对典型样本的学习,建立粗糙集BP神经网络多因素预测模型,将其用于导弹系统研制费用预测。结果表明,该方法减少了网络的训练时间,改善了学习效率,具有较高的预测精度,是可行的、有效的。     

Optimal dealer pricing under transaction uncertainty

Dealers in securities markets are standing ready immediately to trade certain amounts of securities at stated bid and ask prices. This paper assumes that the amount of transactions follows an uncertain mean-reverting process associated with the bid and ask prices. In order to maximize the dealer’s total wealth, an optimal dealer pricing model under transaction uncertainty is established. And the optimal bid price and ask price over time are derived. Finally, the variations of the optimal bid and ask prices with different parameters are presented.     

A strategy of knowledge elicitation for developing an integrated bidding/production management expert system for the precast industry

Bidding and production decisions, including the estimation of optimal mark-up on price, represent major decision problems for companies formulating a successful business strategy. The objective of this research was to develop a strategy for developing an integrated bidding/production management expert system to assess the suitability of incoming enquiries for a particular company and suggests a ‘bid/no bid’ decision. If a decision to bid is taken then the expert system should provide advice on the optimal mark-up to maximise the chance of winning potential contracts. The system developed in this paper is composed of an information system, that integrates design, estimation and production planning, and a knowledge-base to provide abstracted information and advice to managers in charge of bidding. The information system analyses the records of previous contracts and presents managers with vital information that minimises the risk of poor decisions associated with bidding. The knowledge-base is composed of intelligent rules which were elicited from previous contract records and experienced managers in charge of bidding. They are designed to advise managers on two major issues: bid/no bid and estimation of optimal tender price. A number of factors that affect bidding strategies were identified from reviewing previous bidding methodologies and surveying eight major companies in the UK by means of semi-structured interviews.     

Used car salesman problem: A differential auction–barter market

We define a problem called “used car salesman problem” in which sale, purchase and barter bids can be simultaneously put forward for trading cars. A sale or a purchase bid is expressed in terms of a single car and a sale or purchase price that is required for the car. A barter bid, on the other hand, can be augmented by a differential money amount that is offered or required in addition to the cars that are to be traded. Restrictions are also allowed to be placed on sale and purchase bids. A minimum cost circulation network flow algorithm is presented which produces a solution that maximizes the profit made by the used car salesman.AMS subject classification 91B26, 90B10, 05C38     

Two Rules of a Sealed Ceiling Bid and Their Analysis by Mathematical Programming Techniques

Two rules of a sealed ceiling bid for a contract that a firm offering this contract can set are proposed. The rules are such that they encourage the bidders to submit their prices for the contract within a range desirable by the firm so that these prices not to exceed the (unknown to the bidders) price of the bid (the ceiling). It is shown that under certain natural assumptions on the behavior of the bidders, evaluating chances of a firm to award the contract at a price within such a desirable range as a result of the bid conducted in line with the rules is reducible to solving mathematical programming problems on polyhedral sets. It is also shown that under additional assumptions of the same kind, under the proposed rules, the maximum probability to win the bid at a price within the range is higher for each bidder than that under the rule of awarding the contract to a bidder nominated the lowest price. Thus, while serving the interests of the firm, the proposed rules make the bid more attractive to the potential bidders. © 2006 Elsevier Ltd. All rights reserved.