Constructing,evaluating and visualizing value and utility functions for decision support

Formal methods of decision analysis can help to structure a decision making process and to communicate reasons for decisions transparently. Objectives hierarchies and associated value and utility functions are useful instruments for supporting such decision making processes by structuring and quantifying the preferences of decision makers or stakeholders. Common multi-attribute decision analysis software products support such decision making processes but they can often not represent complex preference structures and visualize uncertainty induced by uncertain predictions of the consequences of decision alternatives. To stimulate strengthening these aspects in decision support processes, we propose a set of visualization tools and provide a software package for constructing, evaluating and visualizing value and utility functions. In these tools we emphasize flexibility in value aggregation schemes and consideration and communication of prediction uncertainty. The use of these tools is demonstrated with an illustrative example of river management decision support.     

Fuzzy methods for case-based recommendation and decision support

The paper proposes two case-based methods for recommending decisions to users on the basis of information stored in a database. In both approaches, fuzzy sets and related (approximate) reasoning techniques are used for modeling user preferences and decision principles in a flexible manner. The first approach, case-based decision making, can principally be seen as a case-based counterpart to classical decision principles well-known from statistical decision theory. The second approach, called case-based elicitation, combines aspects from flexible querying of databases and case-based prediction. Roughly, imagine a user who aims at choosing an optimal alternative among a given set of options. The preferences with respect to these alternatives are formalized in terms of flexible constraints, the expression of which refers to cases stored in a database. As both types of decision support might provide useful tools for recommender systems, we also place the methods in a broader context and discuss the role of fuzzy set theory in some related fields.     

Building respectful interface agents

To provide personalized assistance to users, interface agents have to learn not only a user's preferences and interests with respect to a software application, but also when and how the user prefers to be assisted. Interface agents have to detect the user's intention to determine when to assist the user, and the user's interaction and interruption preferences to provide the right type of assistance without hindering the user's work. In this work we describe a user profiling approach that considers these issues within a user profile and a decision making approach that enables the agent to choose the best type of assistance for a given user in a given situation. We also describe the results obtained when evaluating our proposal in the tourism domain, and we compare these results with some previous ones in the calendar management domain.     

Drivers' Mental Representation of Travel Time and Departure Time Choice in Uncertain Traffic Network Conditions

The decisions drivers make, such as choice of route or departure time, constitute typical decision making under uncertainty. Drivers' decision making has been studied within the framework of expected utility theory. However, empirical decisional phenomena violating the premise of expected utility theory have been observed repeatedly. These findings have indicated that decision making is critically affected by the decision frame. It has also been pointed out that the uncertainty of outcome is perceived as an interval of possible resultant values. Based on these findings, we propose hypotheses that: (1) a driver perceives an uncertain travel time as an interval, and (2) a driver decides on a departure time based on a decision frame edited by this interval. To test these hypotheses, we collected data on drivers' departure time choice behavior, n = 335. Decisional phenomena found in this study confirm our hypotheses.     

Complexity results and algorithms for possibilistic influence diagrams

In this article we present the framework of Possibilistic Influence Diagrams (PID), which allows to model in a compact form problems of sequential decision making under uncertainty, when only ordinal data on transitions likelihood or preferences are available. The graphical part of a PID is exactly the same as that of usual influence diagrams, however the semantics differ. Transition likelihoods are expressed as possibility distributions and rewards are here considered as satisfaction degrees. Expected utility is then replaced by anyone of the two possibilistic qualitative utility criteria (optimistic and pessimistic) for evaluating strategies in a PID. We then describe decision tree-based methods for evaluating PID and computing optimal strategies and we study the computational complexity of PID optimisation problems for both cases. Finally, we propose a dedicated variable elimination algorithm that can be applied to both optimistic and pessimistic cases for solving PID.     

枢纽成本约束下的零担物流轴辐式网络设计

针对考虑枢纽建造成本和货物流的不确定的枢纽新建方案问题,引入全寿命周期理论,建立以轴辐式运营网络总成本最小化为目标的混合整数线性规划模型,并提出改进的最大最小后悔值的不确定性决策方法。通过算例来分析投资年限、枢纽干线折扣系数和不确定枢纽建造成本对零担物流（LTL）轴辐式网络的设计的影响。实验结果表明, 采用改进的不确定性决策方法得到的最优方案的运营成本比5个场景的运营成本平均降低了2.17%,表明基于改进的最大最小后悔值的不确定性决策方法,能够降低整个零担物流轴辐式运营网络总成本。     

Adjacent versus coincident representations of geospatial uncertainty: Which promote better decisions?

3D geological models commonly built to manage natural resources are much affected by uncertainty because most of the subsurface is inaccessible to direct observation. Appropriate ways to intuitively visualize uncertainties are therefore critical to draw appropriate decisions. However, empirical assessments of uncertainty visualization for decision making are currently limited to 2D map data, while most geological entities are either surfaces embedded in a 3D space or volumes.This paper first reviews a typical example of decision making under uncertainty, where uncertainty visualization methods can actually make a difference. This issue is illustrated on a real Middle East oil and gas reservoir, looking for the optimal location of a new appraisal well. In a second step, we propose a user study that goes beyond traditional 2D map data, using 2.5D pressure data for the purposes of well design. Our experiments study the quality of adjacent versus coincident representations of spatial uncertainty as compared to the presentation of data without uncertainty; the representations' quality is assessed in terms of decision accuracy. Our study was conducted within a group of 123 graduate students specialized in geology.     

Applying event related potentials to evaluate user preferences toward smartphone form design

Product forms can affect user preference and play an important role in user's purchasing decisions. Neuroimaging methods can provide an improved understanding of the mechanisms of decision making, which enhance the ability of enterprises to effectively design their products. Hence event related potentials (ERPs) were applied to explore the brain activity evoked by variety of product forms when users made preference among them. Smartphone product forms were displayed with equiprobability randomly. Participants were asked to click the left mouse button when they preferred one product form, else the right button for nonpreferred. The brain signals of each participant were recorded by Curry 7.0. Finally, brain signals were processed by using Curry 7.0 SBA and SPSS 18.0 software. The results showed that preferred product forms evoked enhanced N2, P2 and P3. Moreover, there were significant correlation between ERPs and behavioural data, participants devoted more attention and had faster responding time to preferred products than to nonpreferred. These results indicate that the differences of ERPs can be used to evaluate user preference.Relevance to industryThe integration of customer preferences is nowadays a challenge in new product development. Hence a thorough research on the inherent mechanism of preference formation can provide an accurate measurement method of user's perception. The differences of brain signals evoked by product forms can also provide technical support for product designers, which in turn can meet with user experience. Moreover, the results can be taken as evaluating indicators of product design.     

Understanding Perceived Trust to Reduce Regret

Trust is fundamental for promoting the use of online services, such as e‐commerce or e‐health. Understanding how users perceive trust online is a precondition to create trustworthy marketplaces. In this article, we present a domain‐independent general trust perception model that helps us to understand how users make online trust decisions and how we can help them in making the right decisions, which minimize future regret. We also present the results of a user study describing the weight that different factors in the model (e.g., security, look&feel, and privacy) have on perceived trust. The study identifies the existence of a positive correlation between the user's knowledge and the importance placed on factors such as security and privacy. This indicates that the impact factors as security and privacy have on perceived trust is higher in users with higher knowledge.     

Learning a decision maker's utility function from (possibly) inconsistent behavior

When modeling a decision problem using the influence diagram framework, the quantitative part rests on two principal components: probabilities for representing the decision maker's uncertainty about the domain and utilities for representing preferences. Over the last decade, several methods have been developed for learning the probabilities from a database. However, methods for learning the utilities have only received limited attention in the computer science community.

A promising approach for learning a decision maker's utility function is to take outset in the decision maker's observed behavioral patterns, and then find a utility function which (together with a domain model) can explain this behavior. That is, it is assumed that decision maker's preferences are reflected in the behavior. Standard learning algorithms also assume that the decision maker is behavioral consistent, i.e., given a model of the decision problem, there exists a utility function which can account for all the observed behavior. Unfortunately, this assumption is rarely valid in real-world decision problems, and in these situations existing learning methods may only identify a trivial utility function. In this paper we relax this consistency assumption, and propose two algorithms for learning a decision maker's utility function from possibly inconsistent behavior; inconsistent behavior is interpreted as random deviations from an underlying (true) utility function. The main difference between the two algorithms is that the first facilitates a form of batch learning whereas the second focuses on adaptation and is particularly well-suited for scenarios where the DM's preferences change over time. Empirical results demonstrate the tractability of the algorithms, and they also show that the algorithms converge toward the true utility function for even very small sets of observations.     

Exploiting mobility patterns for inter-technology handover in mobile environments

Mobile terminals with multi-radio devices have become increasingly prevalent. This makes it possible for Internet applications to be supported by heterogeneous wireless networks while the terminal is on the move. As the user is constantly moving, it is highly desirable that the terminal connects to the best network and retains high performance of network connections. Handovers can be made within the same type of network (horizontal handover) or different types of networks (vertical handover). This paper focuses on link-layer inter-technology vertical handovers. Vertical handovers present several great challenges, such as user mobility randomness, high handover overhead and optimality requirement. Existing work often focuses only on the current network condition when making handover decisions, ignoring future performance of the terminal. As a result, a handover decision good for the current moment may soon become poor when the user moves to another place. This paper is motivated by the observation that users in a given mobile environment, such as university or enterprise campus, exhibit clear mobility patterns. We propose an approach for making handover decisions, which explicitly exploits user mobility patterns. This approach can produce high-performance handover decisions in the long run. Employing a comprehensive framework for preference customization, the approach supports user customization caring for different user preferences. Extensive real trace driven simulations and comparative study show our algorithm is better than the conventional vertical handover algorithms.     

Normal vector identification and interactive tradeoff analysis using minimax formulation in multiobjective optimization

In multiobjective optimization, tradeoff analysis plays an important role in determining the best search direction to reach a most preferred solution. This paper presents a new explicit interactive tradeoff analysis method based on the identification of normal vectors on a noninferior frontier. The interactive process is implemented using a weighted minimax formulation by regulating the relative weights of objectives in a systematic manner. It is proved under a mild condition that a normal vector can be identified using the weights and Kuhn-Tucker (K-T) multipliers in the minimax formulation. Utility gradients can be estimated using local preference information such as marginal rates of substitution. The projection of a utility gradient onto a tangent plane of the noninferior frontier provides a descent direction of disutility and thereby a desirable tradeoff direction, along which tradeoff step sizes can be decided by the decision maker using an explicit tradeoff table. Necessary optimality conditions are established in terms of normal vectors and utility gradients, which can be used to guide the elicitation of local preferences and also to terminate an interactive process in a rigorous yet flexible way. This method is applicable to both linear and nonlinear (either convex or nonconvex) multiobjective optimization problems. Numerical examples are provided to illustrate the theoretical results of the paper and the implementation of the proposed interactive decision analysis process.     

Integrated evidential reasoning approach in the presence of cardinal and ordinal preferences and its applications in software selection

A combination of cardinal and ordinal preferences in multiple-attribute decision making (MADM) demonstrates more reliability and flexibility compared with sole cardinal or ordinal preferences derived from a decision maker. This situation occurs particularly when the knowledge and experience of the decision maker, as well as the data regarding specific alternatives on certain attributes, are insufficient or incomplete. This paper proposes an integrated evidential reasoning (IER) approach to analyze uncertain MADM problems in the presence of cardinal and ordinal preferences. The decision maker provides complete or incomplete cardinal and ordinal preferences of each alternative on each attribute. Ordinal preferences are expressed as unknown distributed assessment vectors and integrated with cardinal preferences to form aggregated preferences of alternatives. Three optimization models considering cardinal and ordinal preferences are constructed to determine the minimum and maximum minimal satisfaction of alternatives, simultaneous maximum minimal satisfaction of alternatives, and simultaneous minimum minimal satisfaction of alternatives. The minimax regret rule, the maximax rule, and the maximin rule are employed respectively in the three models to generate three kinds of value functions of alternatives, which are aggregated to find solutions. The attribute weights in the three models can be precise or imprecise (i.e., characterized by six types of constraints). The IER approach is used to select the optimum software for product lifecycle management of a famous Chinese automobile manufacturing enterprise.     

Axiomatisation of fully probabilistic design

This text provides background of fully probabilistic design (FPD) of decision-making strategies and shows that it is a proper extension of the standard Bayesian decision making. FPD essentially minimises Kullback–Leibler divergence of closed-loop model on its ideal counterpart. The inspection of the background is important as the current motivation for FPD is mostly heuristic one, while the technical development of FPD confirms its far reaching possibilities. FPD unifies and simplifies subtasks and elements of decision making under uncertainty. For instance, (i) both system model and decision preferences are expressed in common probabilistic language; (ii) optimisation is simplified due to existence of explicit minimiser in stochastic dynamic programming; (iii) DM methodology for single and multiple aims is unified; (iv) a way is open to completion and sharing non-probabilistic and probabilistic knowledge and preferences met in knowledge and preference elicitation as well as unsupervised cooperation of decision makers.     

基于后悔理论及EDAS法的概率语言多属性群决策方法

针对属性权重未知的群体决策问题,提出基于离平均方案（平均解）距离的评价方法（EDAS）及考虑决策者后悔规避心理行为的概率语言术语集（PLTS）多属性群决策方法。首先,根据PLTS的相关性质定义概率语言术语集信息熵及交叉熵并建立属性权重模型;然后,将群体满意度公式拓展到概率语言术语集环境下,并用于后悔理论中效用值的计算;随后,基于概率语言术语集的属性权重确定模型及群体满意度公式,将后悔理论与EDAS法相结合提出新的多属性决策方法,并对各备选方案进行选择排序;最后,以实例网络舆情突发事件的选择排序为实例对所提出的方法进行验证,并通过对比分析来证明所提方法的有效性。     

基于后悔理论及EDAS法的概率语言多属性群决策方法

针对属性权重未知的群体决策问题，提出基于离平均方案（平均解）距离的评价方法（EDAS）及考虑决策者后悔规避心理行为的概率语言术语集（PLTS）多属性群决策方法。首先，根据PLTS的相关性质定义概率语言术语集信息熵及交叉熵并建立属性权重模型；然后，将群体满意度公式拓展到概率语言术语集环境下，并用于后悔理论中效用值的计算；随后，基于概率语言术语集的属性权重确定模型及群体满意度公式，将后悔理论与EDAS法相结合提出新的多属性决策方法，并对各备选方案进行选择排序；最后，以实例网络舆情突发事件的选择排序为实例对所提出的方法进行验证，并通过对比分析来证明所提方法的有效性。     

基于快速连续蚁群算法的QoS切换决策机制

随着人们对移动网络服务需求的日益增长,用户需要在复杂的异构网络中实现不同接入技术之间的无缝切换,因此选择总最佳连接并提供服务质量保证的切换决策成为下一代互联网研究的关键内容.为了更好地满足用户的需求,在综合考虑网络信息的不确定性、用户服务质量需求、用户偏好、用户愿意支付的费用以及网络供应商的收益等因素的前提下,设计了基于快速连续蚁群算法的切换决策机制,并引入协商博弈和Nash均衡思想来解决用户之间的串谋问题以保证切换决策的公平性.仿真结果表明,设计的切换决策机制在满足用户服务质量需求的同时,不仅使双方的效用最大,并且最契合用户的偏好,能够很好地解决下一代互联网中支持总最佳连接的切换决策问题.     

Efficient and non-parametric reasoning over user preferences

We consider the problem of modeling and reasoning about statements of ordinal preferences expressed by a user, such as monadic statement like “X is good,” dyadic statements like “X is better than Y,” etc. Such qualitative statements may be explicitly expressed by the user, or may be inferred from observable user behavior. This paper presents a novel technique for efficient reasoning about sets of such preference statements in a semantically rigorous manner. Specifically, we propose a novel approach for generating an ordinal utility function from a set of qualitative preference statements, drawing upon techniques from knowledge representation and machine learning. We provide theoretical evidence that the new method provides an efficient and expressive tool for reasoning about ordinal user preferences. Empirical results further confirm that the new method is effective on real-world data, making it promising for a wide spectrum of applications that require modeling and reasoning about user preferences.     

Conditional Preference Networks with User's Genuine Decisions

User's choices involve habitual behavior and genuine decision. Habitual behavior is often expressed using preferences. In a multiattribute case, the Conditional Preference Network (CP-net) is a graphical model to represent user's conditional ceteris paribus (all else being equal) preference statements. Indeed, the CP-net induces a strict partial order over the outcomes. By contrast, we argue that genuine decisions are environmentally influenced and introduce the notion of “comfort” to represent this type of choices. In this article, we propose an extension of the CP-net model that we call the CP-net with Comfort (CPC-net) to represent a user's comfort with preferences. Given that preference and comfort might be two conflicting objectives, we define the Pareto optimality of outcomes when achieving outcome optimization with respect to a given CPC-net. Then, we propose a backtrack search algorithm to find the Pareto optimal outcomes. On the other hand, two outcomes can stand in one of six possible relations with respect to a CPC-net. The exact relation can be obtained by performing dominance testing in the corresponding CP-net and comparing the numeric comforts.