Ioanna Arkoudi, Carlos Lima Azevedo, Francisco C. Pereira
arXiv 24 Sep 2021 · Statistics — Machine Learning · publishedTransportation Research Part B Methodological (2023) · 9 citations (OpenAlex)
arXiv:2109.12042 · PDF · DOI · OpenAlex · Extracted main text
This study proposes a novel approach that combines theory and data-driven choice models using Artificial Neural Networks (ANNs). In particular, we use continuous vector representations, called embeddings, for encoding categorical or discrete explanatory variables with a special focus on interpretability and model transparency. Although embedding representations within the logit framework have been conceptualized by Pereira (2019), their dimensions do not have an absolute definitive meaning, hence offering limited behavioral insights in this earlier work. The novelty of our work lies in enforcing interpretability to the embedding vectors by formally associating each of their dimensions to a choice alternative. Thus, our approach brings benefits much beyond a simple parsimonious representation improvement over dummy encoding, as it provides behaviorally meaningful outputs that can be used in travel demand analysis and policy decisions. Additionally, in contrast to previously suggested ANN-based Discrete Choice Models (DCMs) that either sacrifice interpretability for performance or are only partially interpretable, our models preserve interpretability of the utility coefficients for all the input variables despite being based on ANN principles. The proposed models were tested on two real world datasets and evaluated against benchmark and baseline models that use dummy-encoding. The results of the experiments indicate that our models deliver state-of-the-art predictive performance, outperforming existing ANN-based models while drastically reducing the number of required network parameters.
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 | Sifringer, B., Lurkin, V., & Alahi, A (2020) Enhancing discrete choice models with representation learning | 1.000 | 19 | 4 | 100% |
| 2 | Pereira, F. C (2019) Rethinking travel behavior modeling representations through embeddings self | 0.843 | 3 | 3 | 100% |
| 3 | Mikolov, T., Chen, K., Corrado, G., & Dean, J (2013) Efficient estimation of word representations in vector space | 0.644 | 2 | 2 | 100% |
| 4 | Bierlaire, M., Axhausen, K., & Abay, G (2001) The acceptance of modal innovation: The case of Swissmetro | 0.585 | 3 | 1 | 100% |
| 5 | Ben-Akiva, M., McFadden, D., Train, K., Walker, J., Bhat, C., Bierla… (2002) Hybrid choice models: Progress and challenges | 0.511 | 2 | 1 | 100% |
| 6 | Zhao, S., Zhao, T., King, I., & Lyu, M. R (2017) April) | 0.511 | 2 | 1 | 100% |
| 7 | Crawshaw, M (2020) Multi-task learning with deep neural networks: A survey | 0.511 | 2 | 1 | 100% |
| 8 | Yan, B., Janowicz, K., Mai, G., & Gao, S (2017) November) | 0.511 | 2 | 1 | 100% |
| 9 | Feng, S., Cong, G., An, B., & Chee, Y. M (2017) February) | 0.511 | 2 | 1 | 100% |
| 10 | Wang, Z., Li, H., & Rajagopal, R (2020) Urban2Vec: Incorporating Street View Imagery and POIs for Multi-Modal Urban Neighborhood Embedding | 0.511 | 2 | 1 | 100% |
Showing the top 10 of 48 scored citations.
arXiv econ.EM papers that cite this one, ranked by how heavily they lean on it.