Search results

This chapter estimates the demand for flights in an international air travel market using a unique dataset with detailed information not only on flight choices but also on contemporaneous prices and characteristics of all the alternative non-booked flights. The estimation strategy employs a simple discrete choice random utility model that we use to analyze how choices and its response to prices depend on the departing airport, the identity of the carrier, and the departure date and time. The results show that a 10% increase in prices in a 100-seat aircraft throughout a 100-period selling season decreases quantity demanded by 7.7 seats. We also find that the quantity demanded is more responsive to prices for Delta and American, during morning and evening flights and that the response to prices changes significantly over different departure dates.

This article presents the results of a study using discrete choice analysis (DCA) in the dine‐in pizza industry. DCA offers an effective approach for incorporating customer preferences into operating decisions in service businesses. Our results show how customers tradeoff among several determinant attributes (e.g. price, waiting time, quality) when choosing a dine‐in pizza restaurant. The article also offers evidence that managers’ perceptions of customer choice patterns are not the same as customers’ actual choice patterns for the businesses we examined. Finally, we show how our results can be easily incorporated into a decision support system for structuring service operations according to customer preferences.

Facial expression recognition by human observers is affected by subjective components. Indeed there is no ground truth. We have developed Discrete Choice Models (DCM) to capture the human perception of facial expressions. In a first step, the static case is treated, that is modelling perception of facial images. Image information is extracted using a computer vision tool called Active Appearance Model (AAM). DCMs attributes are based on the Facial Action Coding System (FACS), Expression Descriptive Units (EDUs) and outputs of AAM. Some behavioural data have been collected using an Internet survey, where respondents are asked to label facial images from the Cohn–Kanade database with expressions. Different models were estimated by likelihood maximization using the obtained data. In a second step, the proposed static discrete choice framework is extended to the dynamic case, which considers facial video instead of images. The model theory is described and another Internet survey is currently conducted in order to obtain expressions labels on videos. In this second Internet survey, videos come from the Cohn–Kanade database and the Facial Expressions and Emotions Database (FEED).

Discrete choice modeling has been discussed by both academics and practitioners as a means of analytical support for B2C relationship marketing. This paper aims to discuss applying this analytical framework in B2B marketing, with an example of cross‐selling high‐tech services to a large business customer. This example is also used to show how an algorithm of genetic binary choice (GBC) modeling, developed by the author, performs in comparison with major techniques used nowadays, and to analyze the financial impact of these different approaches on profitability of B2B relationship marketing operations.

Predictive models based on the regression analysis, the classification tree and the GBC algorithm are built and analyzed in the context of their performance in optimizing cross‐selling campaigns. An example of business case analysis is used to estimate the financial implications of the different approaches.

B2B relationship marketing, although differing from B2C in many aspects, can also benefit from analytical support with discrete choice modeling. The financial impact of such support is significant, and can be further increased by improving the predictive accuracy of the models. In this context the GBC modeling algorithm proves to be an interesting alternative to the algorithms used nowadays.

The generalizability of the findings, concerning performance characteristics of the algorithms, is limited: which method is best depends, for example, on data distributions and the particular relationships being modeled.

The paper shows how B2B marketing managers can increase the profitability of relationship marketing using discrete choice modeling, and how implementing new algorithms like the GBC model presented here can allow for further improvement.

The paper bridges the gap between research on binary choice modeling and the practice of B2B relationship marketing. It presents a new possibility of analytical support for B2B marketing operations together with financial implications. It also includes a demonstration of an algorithm newly developed by the author.

Stated choice experiments can be used to estimate the parameters in discrete choice models by showing hypothetical choice situations to respondents. These attribute levels in each choice situation are determined by an underlying experimental design. Often, an orthogonal design is used, although recent studies have shown that better experimental designs exist, such as efficient designs. These designs provide more reliable parameter estimates. However, they require prior information about the parameter values, which is often not readily available. Serial efficient designs are proposed in this paper in which the design is updated during the survey. In contrast to adaptive conjoint, serial conjoint only changes the design across respondents, not within-respondent thereby avoiding endogeneity bias as much as possible. After each respondent, new parameters are estimated and used as priors for generating a new efficient design. Results using the multinomial logit model show that using such a serial design, using zero initial prior values, provides the same reliability of the parameter estimates as the best efficient design (based on the true parameters). Any possible bias can be avoided by using an orthogonal design for the first few respondents. Serial designs do not suffer from misspecification of the priors as they are continuously updated. The disadvantage is the extra implementation cost of an automated parameter estimation and design generation procedure in the survey. Also, the respondents have to be surveyed in mostly serial fashion instead of all parallel.

In cooperation with a German online retail bank, the aim of this paper is to investigate how the bank should price a new fee-only financial advisory service. Two types of pricing plans differ in terms of their strategies for determining monthly prices: a fixed monthly price that is identical for all clients (i.e. a flat pricing plan) or a monthly price that varies as a function of each client's assets under management (i.e. a volume pricing plan).

With a discrete choice experiment, this article studies client preferences for the two types of plans. To ensure that the respondents understood the financial consequences of their decisions, a price calculator was embedded into the discrete choice experiment to enable the respondents to determine their individual monthly prices based on their assets under management.

Methodologically, the price calculator is useful for simplifying mathematically complex decisions, and it provides additional valuable information for analysis. Substantively, the results show that clients perceive both types of pricing plans as equally attractive; however, the service provider's revenues would increase by up to 12 per cent if it uses the volume pricing plan.

This research extends the stream of literature on the measurement of pricing plan preferences and offers guidance for service industries, such as telecommunications, cloud computing services, insurances, or transportation. It extends the use of discrete choice experiments to study client preferences for different pricing plans and also integrates a decision aid, i.e. a price calculator, in the experiment to assist clients in comparing alternatives more effectively.

Many consumer-focused corporate social responsibility (CSR) studies suggest a positive link between the responsibility demonstrated by a company and consumers’ intention to favor the company in their purchases. Yet an analogous causal effect between corporate social and financial performances is not evident. This chapter conceptualizes how social desirability and cynicism contribute to the discrepancy between consumers’ attitudes and their actual purchase behavior, and analyzes why consumer choices indicated in surveys do not consistently convert into actions.

We develop a conceptual framework based on hybrid choice modeling to estimate the impact of two new variables, Corporate Social Desirability and Corporate Social Cynicism, on CSR research. The model presented synthesizes research findings from the fields of CSR and psychology with a discrete choice methodology that allows inclusion of psychological aspects as latent variables.

The goal of the framework is to bridge the gap between choices stated by consumers in CSR surveys and their actual choices by quantifying and extracting the effects of biases that otherwise threaten the validity of such survey results. As the next step, the practical value of the model must be evaluated through empirical research combining a CSR choice study with social desirability and cynicism measurement.

The framework proposes a novel way of controlling CSR surveys for potential biases created by social desirability and cynicism and enables quantification of this impact, with potential application to other fields where psychological aspects may distort research results. Future empirical evidence based on the framework may also offer new insights into the mechanisms by which the two biases distort findings.