As people increasingly rely on interactive decision support systems to choose products and make decisions, building effective interfaces for these systems becomes more and more challenging due to the explosion of on-line information, the initial incomplete user preference and user’s cognitive and emotional limitations of information processing. How to accurately elicit user’s preference thereby becomes the main concern of current decision support systems. This paper is a survey of the typical preference elicitation methods proposed by related research works, starting from the traditional utility function elicitation and analytic hierarchy process methods, to computer aided elicitation approaches which include example critiquing, needs-oriented interaction, comparison matrix, CP-network, preferences clustering & matching and collaborative filtering.

Abstract not found

In a previously reported user study, we found that users were able to perform decision tradeoff tasks more efficiently and commit considerably fewer errors with the example critiquing interface than with the ranked list. We concluded that example-based search tools were likely to be useful particularly for extending the scope of consumer e-commerce to more complex products where decision making is critical. This paper presents results from a follow-up user study quantifying the benefits of tradeoff support. Users were able to refine the quality of their preference structures and improve decision accuracy by up to 57 % after performing tradeoff tasks. Tradeoff support also significantly increased users’ confidence in their choices. Together, these two studies show that example critiquing enables users to more accurately find what they want and be confident in their choices, while only requiring a level of effort that is comparable to the ranked list interface. Categories and Subject Descriptors H.5.2 [Information Interfaces and Presentation]: User

In this paper we propose ValueCharts, a set of visualizations and interactive techniques intended to support decision-makers in inspecting linear models of preferences and evaluation. Linear models are popular decision-making tools for individuals, groups and organizations. In Decision Analysis, they help the decisionmaker analyze preferential choices under conflicting objectives. In Economics and the Social Sciences, similar models are devised to rank entities according to an evaluative index of interest. The fundamental goal of building models expressing preferences and evaluations is to help the decision-maker organize all the information relevant to a decision into a structure that can be effectively analyzed. However, as models and their domain of application grow in complexity, model analysis can become a very challenging task. We claim that ValueCharts will make the inspection and application of these models more natural and effective. We support our claim by showing how ValueCharts effectively enable a set of basic tasks that we argue are at the core of analyzing and understanding linear models of preferences and evaluation.

Contingent valuation (CV) plays an important role in policy valuation in domains like environmental management. This research examines sequencing effects when people are asked to value multiple environmental programs and investigates the consistency of responses to different environmental programs using different measures of attitude. In-person interviews using computer-administration were conducted for 190 respondents, half in Raleigh-Durham, NC., and half in Austin, Texas. Respondents evaluated five different environmental programs in each of two sessions, separated by a two-week interval. Half the sample evaluated each program with a willingness-to-pay (WTP) response in the first session and then evaluated the same programs using a set of attitude rating scales in the second session. The other half of the respondents did the tasks in the reverse order. The pattern of WTP responses indicated strong sequencing effects. The WTP amounts were much larger when a good was valued first in a sequence rather than at any point later in a sequence. Contrary to standard economic theory, the total of the WTP amounts for the bundle of five goods was dependent upon which good was evaluated first in a sequence: the more highly valued the first good, the higher the total WTP for all five goods. A comparison of the WTP responses with the attitude rating scales suggested that

We present an approach to the design of personalized recommender systems that integrates content-based methods, collaborative filtering techniques and case-based reasoning while adopting a user-centered perspective. These techniques are employed to support information search and choice processes. In this framework, we developed and tested a system prototype (NutKing) that helps the user to construct a travel plan by recommending attractive travel products or by proposing complete itineraries. In the information search phase, the system aids the user in specifying a successful query that winnows out unwanted products in electronic catalogues and reduces the information overload. This is accomplished through two kinds of query rewriting operators (relaxation and tightening) in a mixed initiative approach. In the choice phase, the search results are sorted according to a case-base similarity metric, which takes into account the similarity between the users' travel preferences. The aim of this adaptive sorting is to highlight products that are potentially interesting, because they are similar to those selected by other users in an analogous context. The prototype has been empirically evaluated in a pilot study. The results of the pilot evaluation are discussed, with special reference to aspects concerning the usersystem interaction aspects.

Based on contrast effects studies from psychology, we predicted that movers arriving from more expensive cities would rent pricier apartments than those arriving from cheaper cities. We also predicted that as people stayed in their new city they would get used to the new prices and would readjust their housing expenditures countering the initial impact of previous prices. We found support for both predictions in a sample of 928 movers from the PSID. Alternative explanations based on unobserved wealth and taste, and on imperfect information are ruled out. ÔCommon Mistake #37: When moving from a high-cost area to a low-cost area, recalibrate your sights...... put the home prices of Boston and San Francisco out of your mind.Õ Eldred (2002, p. 89). The median rent for a two-bedroom apartment in Pittsburgh Pennsylvania is $654. Is that cheap or expensive? The answer seems to depend on what we compare those 654 dollars to. For a mover from San Francisco, Pittsburgh may very well feel like a bargain since the typical two-bedroom in San Francisco rents for $2,124. For a mover from Gadsden, Alabama, on the other hand, Pittsburgh may seem like a rip-off; a typical two-bedroom there rents for just $433.

Preference structures that underlie survey or experimental responses may systematically vary during the administration of such measurement. Maturation, learning, fatigue, and response strategy shifts may all affect the sequential elicitation of respondent preferences at different points in the survey or experiment. The consequence of this phenomenon is that responses and effects can vary systematically within the data set. To capture these structural changes, the authors present a maximum likelihood–based change-point multiple regression methodology that explicitly detects discrete structural changes at various points in time/sequence in regression coefficients by simultaneously estimating the number of change

Economic and participatory methods of project appraisal have traditionally been viewed as mutually exclusive alternatives, as they address different decision making criteria. Participatory methods such citizens' juries (or value juries) have been suggested as a means of better coping with some of the problems associated with economic evaluation methods such as contingent valuation. However, participatory methods have not offered the quantitative outputs of economic methods, nor have they addressed the issue of efficiency in resource allocation. In this paper we compare results from the use of contingent valuation and citizens' juries to appraise a woodland restoration project in Southern Scotland. We also investigate the potential of a third alternative which seeks to combine the strengths of contingent valuation and citizens' juries, the valuation workshop. 3 I.

This paper extends the familiar multi-stage framework for choice by explicitly describing the role that goals play at each stage. We first present a typology of goals, ranging from content to process and from immediate to long-term illustrating it in the context of two examples-- Purchasing a New Car and Earthquake Retrofitting. We then delineate each stage of the choice process based on recent advances from the descriptive literature on the influence of the various goals. Finally, we draw the prescriptive implications as to how goals can inform what we know, or need to know, about the choice process. Key Words: goals, choice process, prescription. 2 In contrast to most formal theories of consumer choice, we propose a framework based on goals. Decision makers attempt to satisfy numerous goals of different types (e.g., consumption, emotion, learning, process, social), given a variety of constraints (e.g., financial, cognitive, affective, temporal). In our view a goal-based theory of choice offers a useful bridge between prescriptive and descriptive consumer decision making.