Discrete Choice and Rational Inattention: A General Equivalence Result

Fosgerau, Mogens; Melo, Emerson; Palma, André de; Shum, Matthew

doi:10.1111/iere.12469

Cited by 48 publications

(37 citation statements)

References 41 publications

(60 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, when consumers have unit demands, complementarities between alternatives are generally ruled out in discrete choice models (McFadden 1978). One exception is the recent work by Fosgerau et al (2017), who show that a demand complementarity effect can arise in a rational inattention model when information costs are modeled using a class of generalized entropies. Our work suggests an alternative mechanism that can lead to the demand complementarity effect, which is driven by consumers' costly acquisition of correlated product information.…”

Section: Related Literaturementioning

confidence: 99%

Informational Complementarity

Lin

2020

Management Science

View full text Add to dashboard Cite

Many products have similar or common attributes and are thus correlated. We show that, when these attributes are uncertain for consumers, a complementarity effect can arise among competing products in the sense that the lower price of one product may increase the demands for the others. This effect occurs when consumers sequentially search for information about both common and idiosyncratic product attributes before purchase. We characterize the optimal search strategy for the correlated search problem, provide the conditions for the existence of the complementarity effect, and show that the effect is robust under a wide range of alternative assumptions. We further explore the implications of the effect for pricing. When firms compete in price, although product correlation may weaken differentiation between the firms, the complementarity effect owing to correlated search may raise equilibrium price and profit. This paper was accepted by Matthew Shum, marketing.

show abstract

Section: Related Literaturementioning

confidence: 99%

Informational Complementarity

Lin

2020

Management Science

View full text Add to dashboard Cite

show abstract

“…We develop a choice model estimation framework with latent constructs that capture information heterogeneity within the data. The key dierence between our work and previous literature is that we show how rational inattention can be framed as a exible and extendable generative learning model that emulates the cognitive processes in human behaviour [113,25]. We postulate that realistic behavioural patterns can be modelled using a data-driven generative learning process, and we estimate a model to represent the underlying heterogeneity of the data.…”

Section: Introductionmentioning

confidence: 58%

“…We propose a generative model framework that extends rational inattentive behaviour in discrete choice, interpreting it as an optimization process rather than a structural model specication. We dierentiate our work from the generalized entropy function described in [113] by framing non-normative behaviour as a learning model allowing for random perturbations to be data-driven. Under this framework, the estimation of a generative model assumes to emulate information processing constraints in rational inattention behaviour and identies observed and latent variable interactions through a neural network interface.…”

Section: Methodsmentioning

confidence: 99%

“…Prospect Theory and Regret Theory [20,30]. The measure of information heterogeneity is closely related to non-normative representation, involving Shannon entropy [113]. Expected utility representation may not be sucient in providing the proper specication for these decision problems as individuals may perceive choice probabilities with dierent levels of uncertainty.…”

Section: Information Theorymentioning

confidence: 99%

“…At the core, DCMs consist of dening a set of rules for Random Utility Maximization (RUM) [27]. For instance, RUM have been been used in estimating route choice models with trac network and socio-demographic information, including regret minimization [32], prospect theory [23] and the rational inattention model [113]. Generative modelling proposes an alternative approach to analyzing travel behaviour data by constructing a model of the underlying distribution using unsupervised learning to generate new data with similar stochastic variations as the population.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Generative Modelling and Machine Learning Methods for Travel Behaviour Analysis

Wong¹

2021

Preprint

View full text Add to dashboard Cite

The dissertation outlines novel analytical and experimental methods for discrete choice modelling using generative modelling and information theory. It explores the influence of information heterogeneity on large scale datasets using generative modelling. The behaviorally subjective psychometric indicators are replaced with a learning process in an artificial neural network architecture. Part of the dissertation establishes new tools and techniques to model aspects of travel demand and behavioural analysis for the emerging transport and mobility markets. Specically, we consider: (i) What are the strengths, weaknesses and role of generative learning algorithms for behaviour analysis in travel demand modelling? (ii) How to monitor and analyze the identiability and validity of the generative model using Bayesian inference methods? (iii) How to ensure that the methodology is behaviourally consistent? (iv) What is the relationship between the generative learning process and realistic representation of decision making as well as its usefulness in choice modelling? and (v) What are the limitations and assumptions that have needed to develop the generative model systems? This thesis is based on four articles introduced in Chapters 3 to 6. Chapters 3 and 4 introduces a restricted Boltzmann machine learning algorithm for travel behaviour that includes an analysis of modelling discrete choice with and without psychometric indicators. Chapter 5 provides an analysis of information heterogeneity from the perspective of a generative model and how it can extract population taste variation using a Bayesian inference based learning process. One of the most promising applications for generative modelling is for modelling the multiple discretecontinuous data. In Chapter 6, a generative modelling framework is developed to show the process and methodology of capturing higher-order correlation in the data and deriving a process of sampling that can account for the interdependencies between multiple outputs and inputs. A brief background on machine learning principles for discrete choice modelling and newly developed mathematical models and equations related to generative modelling for travel behaviour analysis are provided in the appendices.

show abstract

On the uniqueness of quantal response equilibria and its application to network games

Melo

2021

Econ Theory

View full text Add to dashboard Cite

Discrete Choice and Rational Inattention: A General Equivalence Result

Cited by 48 publications

References 41 publications

Informational Complementarity

Informational Complementarity

Generative Modelling and Machine Learning Methods for Travel Behaviour Analysis

On the uniqueness of quantal response equilibria and its application to network games

Contact Info

Product

Resources

About