A methodology for developing Bayesian networks: An application to information technology (IT) implementation

Lauría, Eitel J. M.; Duchessi, Peter

doi:10.1016/j.ejor.2006.01.016

Cited by 66 publications

(30 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…BCNs are probabilistic inference engines that enable analysts to answer queries or perform what-if analyses about the variables in a network. Using a BCN, the impact of changing the value of one or more variables on the remaining variables in the network can be analysed by estimating the values of those variables and providing the associated probabilities (Lauria & Duchessi, 2007). However, this type of analysis cannot be conducted using SWOT-like methods.…”

Section: Introductionmentioning

confidence: 99%

A decision support methodology to enhance the competitiveness of the Turkish automotive industry

Ülengin

Önsel

Aktaş

et al. 2014

European Journal of Operational Research

View full text Add to dashboard Cite

Three levels of competitiveness affect the success of business enterprises in a globally competitive environment: the competitiveness of the company, the competitiveness of the industry in which the company operates and the competitiveness of the country where the business is located. This study analyses the competitiveness of the automotive industry in association with the national competitiveness perspective using a methodology based on Bayesian Causal Networks. First, we structure the competitiveness problem of the automotive industry through a synthesis of expert knowledge in the light of the World Economic Forum's competitiveness indicators. Second, we model the relationships among the variables identified in the problem structuring stage and analyse these relationships using a Bayesian Causal Network. Third, we develop policy suggestions under various scenarios to enhance the national competitive advantages of the automotive industry. We present an analysis of the Turkish automotive industry as a case study. It is possible to generalise the policy suggestions developed for the case of Turkish automotive industry to the automotive industries in other developing countries where country and industry competitiveness levels are similar to those of Turkey.

show abstract

Section: Introductionmentioning

confidence: 99%

A decision support methodology to enhance the competitiveness of the Turkish automotive industry

Ülengin

Önsel

Aktaş

et al. 2014

European Journal of Operational Research

View full text Add to dashboard Cite

show abstract

“…Further, they are independent of the sample size. Finally, Bayesian networks are particularly powerful in representing uncertain knowledge (Ghosh & Valtorta 2000) and permit the analysis of "what-if" questions (Lauría & Duchessi 2007). In general, Bayesian networks can be used either for diagnostic reasoning or predictive reasoning (Korb & Nicholson 2004).…”

Section: The Bayesian Networkmentioning

confidence: 99%

“…Data analysis was performed by means of a Bayesian network, which is an appropriate approach for building models in a context with intrinsic uncertainty (Lauría & Duchessi 2007). Whereas commonly used statistical tests (e.g., structural models) seek to generalize findings and provide statistical significance, their use is questionable in cases of small data samples.…”

Section: The Bayesian Networkmentioning

confidence: 99%

“…Subsequently we empirically test the research model with an experimental research design in the domain of online travel websites. Motivated to focus on causality (Lauría & Duchessi 2007;Zheng & Pavlou 2010), the data are analysed using a Bayesian network approach. Our findings contribute to the information systems (IS) and marketing literature by providing an improved understanding of user satisfaction and the reuse intention of an online store's customers, considering varying degrees of transaction phase support.…”

Section: Australasian Journal Of Information Systemsmentioning

confidence: 99%

See 1 more Smart Citation

Theorizing E-Commerce Business Models: On the Impact of Partially and Fully Supported Transaction Phases on Customer Satisfaction and Loyalty

Madlberger

Matook

2017

AJIS

View full text Add to dashboard Cite

Although considerable research has been conducted on the definition and classification of ecommerce business models, little research has integrated the support and impact of distinct transaction phases within e-commerce business models. Indeed, any channel design decisions depend on the arrangement of the three transaction phases, viz. information phase, agreement phase and fulfilment phase. Whereas in literature, a complete support of transaction phases is implicitly assumed, in practice, e-commerce firms exist that consciously do not support all three transaction phases through the online channel. In cases for which only certain phases are supported in one channel, the customer is required to switch to another channel to complete the transaction. To gain an initial understanding of the relevance of transaction phases, we examine the influence of transaction phase support in one channel on satisfaction and reuse intention of an e-commerce website under consideration of users' prior experiences. We conduct a laboratory experiment involving two e-commerce business models that differ only in the number of supported transaction phases via the online channel. Empirical data was analysed using a Bayesian network approach. Our analysis indicates the types of users who value partial support compared to those users who prefer full support of transaction phases. The results will assist firms in meeting future challenges regarding user engagement and attraction to their online stores.

show abstract

“…Bayesianas não presentes em outros métodos de modelagem é o fato de não ser necessário basear-se em uma teoria ou modelo teórico pré-existente (LAURÍA; DUCHESSI, 2007). Além disso, elas permitem identificar relações não lineares, o tratamento de variáveis multinomiais e a sua aplicação resulta em uma representação gráfica do conhecimento obtido a partir dos dados, possibilitando uma análise mais intuitiva e de compreensão mais simples para o cérebro humano.…”

Section: Sob O Aspecto De Modelagem De Fenômenos Uma Característica unclassified

Uma análise da divisão digital no Brasil através da aplicação da aprendizagem de redes bayesianas

Barreto¹

View full text Add to dashboard Cite

A methodology for developing Bayesian networks: An application to information technology (IT) implementation

Cited by 66 publications

References 36 publications

A decision support methodology to enhance the competitiveness of the Turkish automotive industry

A decision support methodology to enhance the competitiveness of the Turkish automotive industry

Theorizing E-Commerce Business Models: On the Impact of Partially and Fully Supported Transaction Phases on Customer Satisfaction and Loyalty

Uma análise da divisão digital no Brasil através da aplicação da aprendizagem de redes bayesianas

Contact Info

Product

Resources

About