We propose a new multiple criteria decision aiding approach for market segmentation that integrates preference analysis and segmentation decision within a unified framework. The approach employs an additive value func...
详细信息
We propose a new multiple criteria decision aiding approach for market segmentation that integrates preference analysis and segmentation decision within a unified framework. The approach employs an additive value function as the preference model and requires consumers to provide pairwise comparisons of some products as the preference information. To analyze each consumer's preferences, the approach applies the disaggregation paradigm and the stochastic multicriteria acceptability analysis to derive a set of value functions according to the preference information provided by each consumer. Then, each consumer's preferences can be represented by the distribution of possible rankings of products and associated support degrees by applying the derived value functions. On the basis of preference analysis, a new metric is proposed to measure the similarity between preferences of different consumers, and a hierarchical clustering algorithm is developed to perform market segmentation. To help firms serve consumers from different segments with targeted marketing policies and appropriate products, the approach proposes to work out a representative value function and the univocal ranking of products for each consumer so that products that rank in the front of the list can be presented to her/him. Finally, an illustrative example of a market segmentation problem details the application of the proposed approach. (C) 2018 Elsevier Ltd. All rights reserved.
Multiple Criteria Decision Aiding (MCDA) offers a diversity of approaches designed for providing the decision maker (DM) with a recommendation concerning a set of alternatives (items, actions) evaluated from multiple ...
详细信息
Multiple Criteria Decision Aiding (MCDA) offers a diversity of approaches designed for providing the decision maker (DM) with a recommendation concerning a set of alternatives (items, actions) evaluated from multiple points of view, called criteria. This paper aims at drawing attention of the Machine Learning (ML) community upon recent advances in a representative MCDA methodology, called Robust Ordinal Regression (ROR). ROR learns by examples in order to rank a set of alternatives, thus considering a similar problem as preference Learning (ML-PL) does. However, ROR implements the interactive preference construction paradigm, which should be perceived as a mutual learning of the model and the DM. The paper clarifies the specific interpretation of the concept of preference learning adopted in ROR and MCDA, comparing it to the usual concept of preference learning considered within ML. This comparison concerns a structure of the considered problem, types of admitted preference information, a character of the employed preference models, ways of exploiting them, and techniques to arrive at a final ranking.
In this article, incomplete hesitant fuzzy preference relations are under consideration. In order to estimate expressible missing preferences, a hesitant upper bound condition (hubc) is defined for decision makers pre...
详细信息
In this article, incomplete hesitant fuzzy preference relations are under consideration. In order to estimate expressible missing preferences, a hesitant upper bound condition (hubc) is defined for decision makers presenting incomplete information. With the help of this condition, the estimated preference intensities lie inside the defined domain and thus are expressible. An algorithm is proposed to revise minimal possible preferences so that the resultant satisfies property (hubc). Moreover, ranking rule, HF-Borda count, for hesitant fuzzy preference relations is defined. This method dissolves possible ties among alternatives.
Traditionally, a preference on a set A of alternatives is modeled by a binary relation R on A satisfying suitable axioms of pseudo-transitivity, such as the Ferrers condition (aRb and cRd imply and or cRb) or the semi...
详细信息
Traditionally, a preference on a set A of alternatives is modeled by a binary relation R on A satisfying suitable axioms of pseudo-transitivity, such as the Ferrers condition (aRb and cRd imply and or cRb) or the semitransitivity property (aRb and bRc imply and or dRc). In this paper we study (m, n)-Ferrers properties, which naturally generalize these axioms by requiring that a(1)R ... Ra-m and b(1)R ... Rb-n imply a(1)Rb(n) or b(1)Ra(m). We identify two versions of (m, n)-Ferrers properties: weak, related to a reflexive relation, and strict, related to its asymmetric part. We determine the relationship between these two versions of (m, n)-Ferrers properties, which coincide whenever m + n = 4 (i.e., for the classical Ferrers condition and for semitransitivity), otherwise displaying an almost dual behavior. In fact, as m and n increase, weak (m, n)-Ferrers properties become stronger and stronger, whereas strict (m, n)-Ferrers properties become somehow weaker and weaker (despite failing to display a monotonic behavior). We give a detailed description of the finite poset of weak (m, n)-Ferrers properties, ordered by the relation of implication. This poset depicts a discrete evolution of the transitivity of a preference, starting from its absence and ending with its full satisfaction. (C) 2014 Elsevier Inc. All rights reserved.
In this paper, a design decision problem is treated as a multiple criteria decision making (MCDM) problem. Design selection is based upon multiple attribute evaluations for candidate designs and preference judgments o...
详细信息
In this paper, a design decision problem is treated as a multiple criteria decision making (MCDM) problem. Design selection is based upon multiple attribute evaluations for candidate designs and preference judgments on relative importance of attributes. It is intuitively clear that flexibility and a systematic procedure are important features of a technique for acquisition and representation of preference information. This paper is intended to explore a new technique for assigning weights to attributes through a well-defined iterative procedure using minimal preference information. A semi-submersible design problem is then taken as an example to demonstrate how multiple attribute evaluations for candidate designs can be generated and represented and how relative weights of attributes can be assigned using the new weight assignment technique for the ranking of the generated candidate designs.
Decision analysis (DA), a well-established discipline in business and engineering, is entering another domain of application due to the advent of Industry 4.0. DA enables optimal decisions by finding system parameters...
详细信息
Decision analysis (DA), a well-established discipline in business and engineering, is entering another domain of application due to the advent of Industry 4.0. DA enables optimal decisions by finding system parameters that maximize the utility, or in the presence of uncertainty the expected utility, from the attributes of a system. Whether there is a single decision maker or all decision makers have uniform preferences, determining risk behavior and the resulting utility is well developed in the existing literature. However, variability in preferences has not been satisfactorily addressed. This gap gains added significance in the face of the demands of Industry 4.0 where cyberphysical production systems must drive autonomous decision-making on the factory floor. The decisions must accommodate a distribution of customer and designer preferences, including production auditors within the organization. This article provides a novel framework and develops a closed-form approximation for expected utility in the presence of uncertainty in both attributes and preference behaviors. The value of this approach is demonstrated in the assembly of parts in a cyberphysical production system of an automotive manufacturing plant. The comparison of corrective assembly using the proposed method with existing random assembly approaches shows significant improvements.
The integration of customer preferences is nowadays a challenge in new product development. In this paper, we describe a method which integrates the customer preferences for the design of geometrical forms. We illustr...
详细信息
The integration of customer preferences is nowadays a challenge in new product development. In this paper, we describe a method which integrates the customer preferences for the design of geometrical forms. We illustrate the approach by the design of a car's headlight. From a product space, the method is based on the definition of a perceptual space, built by multidimensional scaling, and which lead to the definition of interpretable perceptual dimensions. Objective measures of the form, computed from the design variables of the design model, are selected to interpret the perceptual dimensions. These measures are representative of the overall form and of the curvature variations. At this level, the Fourier coefficients of a closed curve are used to represent the information on the curvature variations. Next, from the preferences of a customer, the target values of the selected measures corresponding to a preference optimum are calculated. We show in the paper the interest of this approach for the design of forms. The method is illustrated by the design of a car's headlight, modeled by Bezier curves and integrated in a front-end.
When handling preferences, the inclusion-based partial order (called here Pareto dominance) is a natural basis for comparing solutions: one is then preferred to another as soon as the set of preferences violated by th...
详细信息
ISBN:
(纸本)9783030794569;9783030794576
When handling preferences, the inclusion-based partial order (called here Pareto dominance) is a natural basis for comparing solutions: one is then preferred to another as soon as the set of preferences violated by the former is a subset of the preferences violated by the latter. In order to obtain refinements of this partial order, various general principles can be used, such as Ceteris Paribus, or optimistic (resp. pessimistic) principles stating that what is not explicitly said to be satisfactory according to the preferences should be regarded as satisfactory (resp. disregarded). Algorithms taking advantage of the two last principles are presented and discussed. They enable us to refine the Pareto ordering of solutions.
This study examines the impact of the "diversity" of product recommendations on the "preference" of a customer, using online/offline data from a leading fashion company. First, through interviews w...
详细信息
ISBN:
(纸本)9781450368599
This study examines the impact of the "diversity" of product recommendations on the "preference" of a customer, using online/offline data from a leading fashion company. First, through interviews with fashion professionals, we categorized the characteristics of customers into four types - gift, coordinator, carry-over, and trendsetter. Then, using a hybrid filtering method, we increased the accuracy and diversity of recommended products. We derived 13 salient features that reflect customer behavior based on the Purchase Funnel model and built a classification model that predicts a customer's preference rates. Second, we conducted two large-scale user tests with 20,000 real customers to verify the effectiveness of our recommendation system. Study results empirically demonstrated the importance of diversity of recommended products. The more diverse the product recommendations were, the higher the purchase rate, the average purchase amount, and the cross purchase rate were observed. In addition, we tracked the customers' purchase for two months after the user tests and found that diverse product exposure positively influenced customer retention (e.g., repurchase rate, amount).
A team formation problem consists in finding an effective group of experts in a social network to accomplish a job with a minimum expenditure of energy and time. This problem has been transposed into the domain of mul...
详细信息
ISBN:
(数字)9783319647982
ISBN:
(纸本)9783319647982;9783319647975
A team formation problem consists in finding an effective group of experts in a social network to accomplish a job with a minimum expenditure of energy and time. This problem has been transposed into the domain of multiagent systems to form a team of autonomous agents whose mission is to achieve a given goal. There is a wide range of such problems. This paper generalizes one of them by assigning explicit behaviors to agents whose tasks are equipped with multiple attributes. Their values are compared with preferences attached to the desired tasks of the goal. A synthesized controller realizes the goal by invoking tasks of a subset of the available agents, called a composition in this paper. Furthermore, utility values are assigned to compositions and robustness is considered to be an important property of a team to prevent its deterioration when one or more of its agents fail. Finding a robust team that satisfies the goal's preferences with better utility values for compositions constitutes a difficult optimization problem. The proposed method to solve this problem consists in three phases: controller synthesis with filtering on tasks with respect to some qualitative preferences, composition ranking based on their fitness, and multiobjective mathematical optimization.
暂无评论