Model Of Consumer Preferences Research Articles

Diffstrat: An analytical procedure for generating optimal new product concepts for a differentiated-type strategy

Firms are likely to consider employing multiple products in markets where competition and heterogeneity of consumer preferences suggest the use of market segmentation. The problem of identifying the optimal multiple new product concepts for such a market may be considered in either a sequential (one product at a time) or a simultaneous fashion. We show that the ‘optimal’ new product concepts generated sequentially are different from, and generality inferior to, those generated simultaneously. In this paper we present a new procedure, Diffstrat, which solves this problem of generating simultaneously optimal multiple new products for a wide range of consumer preference models. This procedure utilizes a fundamental insight called the augmented space approach to solve this problem.

The Cost of Simplifying Preference Models

Formulas are derived which estimate the accuracy of conjoint analysis in predicting preferences in a validation sample. This accuracy turns out to depend on (among other things) which model of preference is used (e.g., whether interactions are added, whether partworth or linear functions are used). I first show a paradoxical result that simpler models often yield higher predictive accuracy, even when a more complex model is the true one. The reason for this is that the additional parameters of the complex model are estimated with larger variance, which tends to overwhelm the benefits of using the true model. I then shift my criterion from predicting an individual's preferences, to predicting market share, which is of most interest to managers. Under this criterion my conclusions reverse, and I show that a true model (even when complex) is much more likely to yield higher predictive accuracy than a simpler incorrect model. This reverses some previous conclusions in marketing, and confirms that finding the correct model of consumer preference is important in improving prediction. Results from four previous empirical papers are correctly predicted by these formulas, as well as results from additional Monte Carlo studies.

Costs and benefits of peak-load pricing of electricity: A continuous-time econometric approach

We address the following question of current policy interest: Would the efficiency gains from residential time-of-use pricing for electricity exceed the metering costs necessitated by these more complex rates? A model of consumer preferences for daily electricity consumption is estimated based on data from the North Carolina Rate Experiment. The model is formulated in continuous time and thus is capable of evaluating demand responses and welfare consequences of quite arbitrary changes in pricing policy. A model of long-run electricity costs - viewed as a functional of the daily load cycle - is constructed based on engineering data. The models of demand and cost are combined to compute solutions to several optimal pricing problems and to estimate the potential long-run welfare gain from several alternative time-of-use pricing policies including policies incorporating so-called ‘demand charges’. We find that the best of the rate treatments used in the North Carolina experiment achieves a net welfare gain of 5¢ per day per household, or roughly half the cost of current metering equipment. Smoothly varying rates are capable of achieving nearly 18¢ per day per household, but would require more complex metering. Demand charges while they are quite successful in smoothing the demand cycle are not as successful as conventional pricing policies in achieving our welfare objective.

A Comparative Evaluation of Multiattribute Consumer Preference Models

In this paper the theory and estimation procedures for several consumer preference models are discussed. Predictive accuracy in the form of internal consistency of these models is compared in an empirical application. Consumer decision situations are classified into two classes: decisions under certainty and decisions under uncertainty. For each of the two classes of decision situations two modeling strategies have been used: statistical estimation and algebraic solution. An additive conjoint, an additive and a multiplicative measurable value, and an additive and a multiplicative utility model are considered. Our main finding is that the statistical estimation procedures outperform their algebraic counterparts on the criterion of predictive accuracy. The utility model provides better predictions for decisions under uncertainty than the widely used conjoint models. The relationship between models for decisions under certainty and decisions under uncertainty is discussed. It is shown how a conjoint or a measurable value function model can be transformed into a utility model with minimum additional information from the subjects. A concept of relative risk attitude is proposed to segment consumers by the degree of their risk aversion or risk seeking propensities.

A Consumer Preference Approach to the Planning of Rural Primary Health-Care Facilities

A problem in planning the expansion of a rural primary health-care delivery system is to determine the set of facilities to be added to an existing system so as to maximize the incremental benefit to the community subject to a cost constraint. The proposed approach involves the following five steps: (1) identification of facility attributes relevant to patients in their choice of health-care facilities, (2) modeling of an individual's overall preference for alternate facilities as a weighted linear function of these facility attributes, (3) transformation of each consumer's preference model into a benefit function expressing the individual's benefit in dollars/year for an existing or potential facility, (4) provision of a method for determining the total incremental benefit to the community from a set of proposed health-care facilities, and (5) use of a heuristic procedure to determine a set of facilities that yields near-optimum total incremental benefit subject to the cost constraint. A practical application of the proposed approach reveals that the consumer preference model has substantial reliability and predictive validity.

Scheduling a Fixed-Schedule, Common Carrier Passenger Transportation System

This paper presents a method for developing efficient timetables for the operation of fixed schedule common-carrier passenger transportation systems. The ability to compute such timetables is needed in the consideration of planning alternatives for future transportation systems and for the efficient operation of existing systems. Here, timetable optimization is accomplished by maximizing an objective function consisting of three basic components: operating costs, revenues, and traveler benefits. Traveler benefits are computed using a consumer preference model that specifies a traveler's willingness to pay for alternative trips, based on the scheduling of those trips. The optimization is based on successive iterations of a dynamic programming algorithm that develops timetables for each vehicle in the system. Solutions are termed optimal to within a “first-order passenger exchange.” Examples are presented to illustrate the utilization of the methodology for computing information relevant to the development of system operating policies and to the consideration of planning alternatives.