You have already added 0 works in your ORCID record related to the merged Research product.
Bayesian Automatic Relevance Determination for Utility Function Specification in Discrete Choice Models
Copyright policy )Specifying utility functions is a key step towards applying the discrete choice framework for understanding the behaviour processes that govern user choices. However, identifying the utility function specifications that best model and explain the observed choices can be a very challenging and time-consuming task. This paper seeks to help modellers by leveraging the Bayesian framework and the concept of automatic relevance determination (ARD), in order to automatically determine an optimal utility function specification from an exponentially large set of possible specifications in a purely data-driven manner. Based on recent advances in approximate Bayesian inference, a doubly stochastic variational inference is developed, which allows the proposed DCM-ARD model to scale to very large and high-dimensional datasets. Using semi-artificial choice data, the proposed approach is shown to very accurately recover the true utility function specifications that govern the observed choices. Moreover, when applied to real choice data, DCM-ARD is shown to be able discover high quality specifications that can outperform previous ones from the literature according to multiple criteria, thereby demonstrating its practical applicability.
21 pages, 2 figures, 11 tables
Microsoft Academic Graph classification: Relevance (information retrieval) Computer science Key (cryptography) Bayesian probability Inference Bayesian inference Machine learning computer.software_genre computer Scale (descriptive set theory) Artificial intelligence business.industry business Discrete choice Function (engineering) media_common.quotation_subject media_common
Computer Science Applications, Mechanical Engineering, Automotive Engineering, Statistics - Machine Learning, Computer Science - Machine Learning, discrete choice models, automatic relevance determination, automatic utility specification, doubly stochastic variational inference, variable selection, machine, prediction, regression, Machine Learning (stat.ML), Machine Learning (cs.LG), FOS: Computer and information sciences
Computer Science Applications, Mechanical Engineering, Automotive Engineering, Statistics - Machine Learning, Computer Science - Machine Learning, discrete choice models, automatic relevance determination, automatic utility specification, doubly stochastic variational inference, variable selection, machine, prediction, regression, Machine Learning (stat.ML), Machine Learning (cs.LG), FOS: Computer and information sciences
Microsoft Academic Graph classification: Relevance (information retrieval) Computer science Key (cryptography) Bayesian probability Inference Bayesian inference Machine learning computer.software_genre computer Scale (descriptive set theory) Artificial intelligence business.industry business Discrete choice Function (engineering) media_common.quotation_subject media_common
- Ecole Polytechnique Fédéral de Lausanne United Arab Emirates
- École Polytechnique Fédérale de Lausanne Switzerland
- École polytechnique fédérale de Lausanne
- Ecole Polytechnique Federale de Lausanne
- EPFL Switzerland
2813
Bierlaire, M., Axhausen, K., & Abay, G. (2001). The acceptance of modal innovation: The case of swissmetro. In Proceedings of the 1st Swiss Transportation Research Conference .
Bishop, C. M. (2006). Pattern recognition and machine learning . springer.
Blei, D. M., La erty, J. D. et al. (2007). A correlated topic model of science. The Annals of Applied Statistics , 1 , 17{35. [OpenAIRE]
Brathwaite, T., & Walker, J. L. (2018). Asymmetric, closed-form, nite-parameter models of multinomial choice. Journal of choice modelling , 29 , 78{112. [OpenAIRE]
Brusco, M. J. (2014). A comparison of simulated annealing algorithms for variable selection in principal component analysis and discriminant analysis. Computational Statistics & Data Analysis , 77 , 38 { 53.
Danaf, M. (2017). Personalized recommendations using discrete choice models with inter-and intra-consumer heterogeneity. In International Choice Modelling Conference 2017 .
Dash, M., & Liu, H. (1997). Feature selection for classi cation. Intelligent Data Analysis, 1 , 131{156.
Deng, H., & Runger, G. (2012). Feature selection via regularized trees. In Neural Networks (IJCNN), The 2012 International Joint Conference on (pp. 1{8). IEEE. [OpenAIRE]
Drugowitsch, J. (2013). Variational bayesian inference for linear and logistic regression. arXiv preprint arXiv:1310.5438 , . [OpenAIRE]
Fouskakis, D., & Draper, D. (2008). Comparing stochastic optimization methods for variable selection in binary outcome prediction, with application to health policy. Journal of the American Statistical Association , 103 , 1367{1381. [OpenAIRE]
- Ecole Polytechnique Fédéral de Lausanne United Arab Emirates
- École Polytechnique Fédérale de Lausanne Switzerland
- École polytechnique fédérale de Lausanne
- Ecole Polytechnique Federale de Lausanne
- EPFL Switzerland
- EPFL Switzerland
- Ecole polytechnique fédérale de Lausanne
- École Polytechnique Fédérale de Lausanne
- Ecole Polytechnique Fédérale de Lausanne (EPFL)
- Ecole Polytechnique Federal de Lausanne
- Ecole Polytechnique Féréérale de Lausanne
- EPFL
- Ecole Polytechnique Fédérale de Lausanne EPFL Switzerland
- Ecole Polytechnique Fédérale de Lausane
- Technical University of Denmark Denmark
Specifying utility functions is a key step towards applying the discrete choice framework for understanding the behaviour processes that govern user choices. However, identifying the utility function specifications that best model and explain the observed choices can be a very challenging and time-consuming task. This paper seeks to help modellers by leveraging the Bayesian framework and the concept of automatic relevance determination (ARD), in order to automatically determine an optimal utility function specification from an exponentially large set of possible specifications in a purely data-driven manner. Based on recent advances in approximate Bayesian inference, a doubly stochastic variational inference is developed, which allows the proposed DCM-ARD model to scale to very large and high-dimensional datasets. Using semi-artificial choice data, the proposed approach is shown to very accurately recover the true utility function specifications that govern the observed choices. Moreover, when applied to real choice data, DCM-ARD is shown to be able discover high quality specifications that can outperform previous ones from the literature according to multiple criteria, thereby demonstrating its practical applicability.
21 pages, 2 figures, 11 tables