Predição de Séries Temporais de Demanda em Modelos de Compartilhamento de Veículos para Modelos Uni e Multi Variáveis

• Victor Aquiles Soares de Barros Alencar Universidade Federal de Juiz de Fora
• Lucas Ribeiro Pessamilio Universidade Federal de Juiz de Fora
• Felipe Rooke da Silva Universidade Federal de Juiz de Fora http://orcid.org/0000-0001-5625-2694
• Heder Soares Bernardino Universidade Federal de Juiz de Fora
• Alex Borges Vieira Universidade Federal de Juiz de Fora

DOI: https://doi.org/10.5753/courb.2020.12355

Abstract

Car sharing is an alternative to urban mobility that has been widely adopted. However, this approach is prone to several problems, such as fleet imbalance, due to the dayli demands variance in large urban centers. In this work, we apply two time series techniques, the LSTM and the Prophet, to infer the demand for three real car sharing services. In addition to historical data, we also use climatic attributes in the LSTM applications. As a result, it was observed that the addition of meteorological data improved the model’s performance: an average MAE (Mean Absolute Error) of approximately 6.01% is obtained with the demand data, while an average MAE equals to 5.9% is observed when adding the climatic data. One can also notice that the LSTM’s performance is better than that obtained by Prophet (average MAE equal to 10.4%) for the databases adopted here and considering only the demand for services.

Keywords: Séries Temporais, Car-sharing, Mobilidade Urbana

References

Alencar, V. A., Rooke, F., Cocca, M., Vassio, L., Almeida, J., and Vieira, A. B. (2019).Characterizing client usage patterns and service demand for car-sharing systems. Information Systems, page 101448.

Boldrini, C., Bruno, R., and Conti, M. (2016). Characterising demand and usage patterns in a large station-based car sharing system. In Computer Communications Workshops (INFOCOM WKSHPS), 2016 IEEE Conference on, pages 572-577. IEEE.

Cocca, M., Teixeira, D., Vassio, L., Mellia, M., Almeida, J. M., and Couto da Silva, A. P.(2020). On car-sharing usage prediction with open socio-demographic data. Electronics, 9(1):72.

Hamari, J., Sjóklint, M., and Ukkonen, A. (2016). The sharing economy: Why people participate in collaborative consumption. Journal of the association for information science and technology, 67(9):2047-2059.

Laptev, N., Yosinski, J., Li, L. E., and Smyl, S. (2017). Time-series extreme event forecasting with neural networks at uber. In International Conference on Machine Learning, volume 34, pages 1-5.

Müller, J. and Bogenberger, K. (2015). Time series analysis of booking data of a free-floating carsharing system in berlin. Transportation Research Procedia, 10:345-354.

Nourinejad, M. (2014). Dynamic optimization models for ridesharing and carsharing. Master's thesis, University of Toronto.

Papacharalampous, G., Tyralis, H., and Koutsoyiannis, D. (2018). Predictability of monthly temperature and precipitation using automatic time series forecasting methods. Acta Geophysica, 66(4):807-831.

Samal, K., Babu, K. S., Das, S. K., and Acharaya, A. (2019). Time series based air pollution forecasting using sarima and prophet model. In Proceedings of the 2019 International Conference on Information Technology and Computer Communications, pages 80-85. ACM.

Shaheen, S. A. (2016). Mobility and the sharing economy. Transport Policy, 51(Supplement C):141 — 142.

Taylor, S. J. and Letham, B. (2018). Forecasting at scale. The American Statistician, 72(1):37-45.