Untitled

Keane, Michael P.

doi:10.1023/a:1007912614003

Cited by 48 publications

(6 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…What accounts for this phenomenon? As we've seen, one explanation is the inventory-planning behavior that Keane (1997a) predicted would cause such a problem. 7 In response, several authors, such as Erdem et al (2003), Sun et al (2003) and Hendel and Nevo (2004), have proposed abandoning conventional static choice models (i.e., MNL and NMNL) in favor of dynamic structural inventory-planning models.…”

mentioning

confidence: 83%

“…As Keane (1997a) notes, the exaggeration of the elasticity could be even greater if consumers are able to anticipate future sales. For example, suppose a retailer always puts brand A on sale in week 2 of every 5 week period.…”

Section: Introductionmentioning

confidence: 99%

“…CHING, T. ERDEM AND M. KEANE An important paper by Sun et al (2003) shows that the problems with conventional choice models noted by Keane (1997a) are not merely academic. They conduct two experiments.…”

mentioning

confidence: 99%

See 2 more Smart Citations

The price consideration model of brand choice

Ching

Erdem

Keane

2009

J of Applied Econometrics

Self Cite

View full text Add to dashboard Cite

SUMMARYThe workhorse brand choice models in marketing are the multinomial logit (MNL) and nested multinomial logit (NMNL). These models place strong restrictions on how brand share and purchase incidence price elasticities are related. In this paper, we propose a new model of brand choice, the "price consideration" (PC) model, that allows more flexibility in this relationship. In the PC model, consumers do not observe prices in each period. Every week, a consumer decides whether to consider a category. Only then does he/she look at prices and decide whether and what to buy. Using scanner data, we show the PC model fits much better than MNL or NMNL. Simulations reveal the reason: the PC model provides a vastly superior fit to inter-purchase spells.

show abstract

mentioning

confidence: 83%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

The price consideration model of brand choice

Ching

Erdem

Keane

2009

J of Applied Econometrics

Self Cite

View full text Add to dashboard Cite

show abstract

“…The goal of this study is to present generative models as a behaviourally intuitive representation of travel decision making with an endogenous learning process. We argue that the main advantage of generative machine learning is that we can rely less on hypothesis driven behaviour assumptions and representing decision perturbations beyond unobserved utility terms [10]. Recent developments in artificial neural network and learning algorithms have made it possible to estimate complex and non-rational behaviour (relaxation of IID assumptions) models that generalize better to various decision making strategies [11].…”

Section: Introductionmentioning

confidence: 99%

A bi-partite generative model framework for analyzing and simulating large scale multiple discrete-continuous travel behaviour data

Wong

Farooq

2020

Transportation Research Part C: Emerging Technologies

View full text Add to dashboard Cite

The emergence of data-driven demand analysis have led to the increased use of generative modelling to learn the probabilistic dependencies between random variables. Although their apparent use has largely been limited to image recognition and classification in recent years, generative machine learning algorithms can be a powerful tool for travel behaviour research by replicating travel behaviour by the underlying properties of data structures. In this paper, we examine the use of generative machine learning approach for analyzing multiple discrete-continuous (MDC) travel behaviour data. We provide a plausible perspective of how we can exploit the use of machine learning techniques to interpret the underlying heterogeneities in the data. We show that generative models are conceptually similar to choice selection behaviour process through information entropy and variational Bayesian inference. Without loss of generality, we consider a restricted Boltzmann machine (RBM) based algorithm with multiple discrete-continuous layer, formulated as a variational Bayesian inference optimization problem. We systematically describe the proposed machine learning algorithm and develop a process of analyzing travel behaviour data from a generative learning perspective. We show parameter stability from model analysis and simulation tests on an open dataset with multiple discrete-continuous dimensions from a data size of 293,330 observations. For interpretability, we derive the conditional probabilities, elasticities and perform statistical analysis on the latent variables. We show that our model can generate statistically similar data distributions for travel forecasting and prediction and performs better than purely discriminative methods in validation. Our results indicate that latent constructs in generative models can accurately represent the joint distribution consistently on MDC data.

show abstract

“…However, the problem with the multinomial logit is that it makes very strong assumptions about consumer behavior. The assumption that has received the most attention is the independence of irrelevant alternatives (IIA) property, which says that if a new alternative is added to a choice set then choice probabilities for all existing alternatives fall proportionately [16]. If the IIA property holds, it is possible, for example, to reduce a number of choice alternatives without influencing the relations among the remaining ones.…”

mentioning

confidence: 99%

Measuring Tourists’ Preferences – Which Road to Choose?

Ferreira

Pereira²

2014

J Tourism Hospit

View full text Add to dashboard Cite

EditorialThe continuous growth in the tourism industry leads that destinations today must compete more than ever to attract tourists. Understanding destination competitiveness and attractiveness as well as modeling and forecasting tourism demand are critical to decision makers and destination managers, since it is known that tourism affects their regional and national economy through direct and indirect tourism revenues. For example, Song and Witt [1] refer that estimates of future tourism demand constitute a very important element in all planning activities of tourism-related business and, consequently, have a key role as a determinant of their profitability. Furthermore, Dwyer and Kim [2] mention that destination competitiveness would appear to be linked to the ability of a destination to deliver goods and services that perform better than other destinations on those aspects of the tourism experience considered to be important by tourists, because tourists would be expected to choose the destination that generates the highest level of utility.To assess the performance of a destination at aggregate level (e.g. at country or region levels), researchers have developed several different approaches to measure destination competitiveness using a large set of indicators and a wide range of methodologies. Some have used survey data of tourists' perceptions to measure competiveness [2][3][4][5]. Others have used published data (about the economy, environment, infrastructure, etc) to assess and compare the competitiveness of tourist destinations across a range of countries [6]. However, as far as we know, none of these researches have included an indicator of consumers' preferences, which was considered by Dwyer et al. [7], one of the three main elements of tourism demand as determinant of tourism competitiveness.At less aggregate levels, destination attractiveness and market share have been studied using stated preferences methods. Discrete choice modeling in economic theory complies with lancaster's new approach to the individual utility maximization problem in consumer theory [13] and with the random utility theory [14,15]. Discrete choice-based approaches use the random utility function where the stochastic component includes all unidentified factors that affect choices. Under the random utility theory, individual preference can be elicited by asking respondents to rank a set of alternative options from most to least preferred (contingent ranking data) or to choose their most preferred option (first-choice data). The measurement scale for the dependent variable determines the model to be estimated.With first-choice data, the choice experiment determines the multinomial logit, which is the most commonly used discrete choice model [14]. The appeal of the multinomial logit arose from the fact that it is simple to estimate. However, the problem with the multinomial logit is that it makes very strong assumptions about consumer behavior. The assumption that has received the most attention is the independence of irrelevant...

show abstract

Untitled

Cited by 48 publications

References 35 publications

The price consideration model of brand choice

The price consideration model of brand choice

A bi-partite generative model framework for analyzing and simulating large scale multiple discrete-continuous travel behaviour data

Measuring Tourists’ Preferences – Which Road to Choose?

Contact Info

Product

Resources

About