arXiv 31 Aug 2019 · Econometrics · 10 citations (OpenAlex)
arXiv:1909.00154 · PDF · DOI · OpenAlex · Extracted main text
This paper introduces the concept of travel behavior embeddings, a method for re-representing discrete variables that are typically used in travel demand modeling, such as mode, trip purpose, education level, family type or occupation. This re-representation process essentially maps those variables into a latent space called the embedding space. The benefit of this is that such spaces allow for richer nuances than the typical transformations used in categorical variables (e.g. dummy encoding, contrasted encoding, principal components analysis). While the usage of latent variable representations is not new per se in travel demand modeling, the idea presented here brings several innovations: it is an entirely data driven algorithm; it is informative and consistent, since the latent space can be visualized and interpreted based on distances between different categories; it preserves interpretability of coefficients, despite being based on Neural Network principles; and it is transferrable, in that embeddings learned from one dataset can be reused for other ones, as long as travel behavior keeps consistent between the datasets. The idea is strongly inspired on natural language processing techniques, namely the word2vec algorithm. Such algorithm is behind recent developments such as in automatic translation or next word prediction. Our method is demonstrated using a model choice model, and shows improvements of up to 60% with respect to initial likelihood, and up to 20% with respect to likelihood of the corresponding traditional model (i.e. using dummy variables) in out-of-sample evaluation. We provide a new Python package, called PyTre (PYthon TRavel Embeddings), that others can straightforwardly use to replicate our results or improve their own models. Our experiments are themselves based on an open dataset (swissmetro).
appendix boundary found by none_found · 100% of the source is main text. Read the extracted text to check this.
The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.
| Reference | Intensity | Mentions | Sections | Main text | |
|---|---|---|---|---|---|
| 1 | M. Bierlaire, K. Axhausen, G. Abay, The acceptance of modal innovati… (2001) | 0.644 | 2 | 2 | 100% |
| 2 | Inferring dynamic origin-destination flows by transport mode using m… (2019) 254 – 275 | 0.511 | 2 | 1 | 100% |
| 3 | T. Brathwaite, J. L. Walker, Asymmetric, closed-form, finite-paramet… (2018) 78–112 | 0.511 | 2 | 1 | 100% |
| 4 | Fasttext - embeddings for 157 languages, https://fasttext.cc, accessed (2019) -06-19 | 0.511 | 2 | 1 | 100% |
| 5 | Word2vec tutorial - the skip-gram model, http://mccormickml.com/ (2016) /04/19/word2vec-tutorial-the-skip-gram-model/, accessed: 2019-06-30 | 0.511 | 2 | 1 | 100% |
| 6 | N. Arora, G. M. Allenby, J. L. Ginter, A hierarchical bayes model of… (1998) 29–44 | 0.405 | 1 | 1 | 100% |
| 7 | M. E. Ben-Akiva, S. R. Lerman, S. R. Lerman, Discrete choice analysi… (1985) | 0.405 | 1 | 1 | 100% |
| 8 | M. J. Davis, Contrast coding in multiple regression analysis: Streng… (2010) 61–73 | 0.405 | 1 | 1 | 100% |
| 9 | Y. Goldberg, O. Levy, word2vec explained: deriving mikolov et al.'s… | 0.405 | 1 | 1 | 100% |
| 10 | D. Guthrie, B. Allison, W. Liu, L. Guthrie, Y. Wilks, A closer look… (2006) pp | 0.405 | 1 | 1 | 100% |
Showing the top 10 of 15 scored citations.
arXiv econ.EM papers that cite this one, ranked by how heavily they lean on it.