Modelos de aprendizagem de máquina para a gestão estratégica de bicicletas compartilhadas / Machine learning models for shared bicycle strategic management

Johnattan Douglas Ferreira Viana, Thalia Katiane Sampaio Gurgel, Lenardo Chaves e Silva, Sebastião Emidio Alves Filho, Carlos Heitor Pereira Liberalino, Álvaro Alvares de Carvalho César Sobrinho

Abstract


Os Sistemas de Bicicletas Compartilhadas são cada vez mais comuns nas cidades, evidenciando a relevância de abordagens que auxiliem na tomada de decisão e gestão estratégica das empresas responsáveis por esses sistemas. Neste trabalho, é apresentado uma versão estendida de um estudo de caso no sistema Capital BikeShare (Washington, D.C.) com o objetivo de realizar uma análise estatística para identificar a relação entre o clima e o serviço de aluguel de bicicletas, além de aplicar algoritmos de aprendizagem de máquina para classificar a quantidade de aluguéis. Como adicional desta versão, apresenta-se uma abordagem de agrupamentos das estações de aluguéis, que resultou em uma acurácia de 94,7%, maior do que a obtida anteriormente. Os resultados apresentados evidenciam que o agrupamento das estações, além de aumentar a acurácia dos modelos preditivos, também facilitam a aplicação desses modelos preditivos na prática. Dessa forma, os modelos preditivos apresentados são mecanismos eficientes que permitem gerenciar esses sistemas, adotando estratégias de negócios baseadas na previsão do tempo e nas estações do ano.

  

Keywords


Sistemas de Bicicletas Compartilhadas. Mineração de Dados. Gestão Estratégica.

References


REFERÊNCIAS

Becker, R. (2018). The new S language. CRC Press.

Borgnat, P., Robardet, C., Rouquier, J. B., Abry, P., Fleury, E., e Flandrin, P. (2011). Shared Bicycles in a City: A Signal Processing and Data Analysis Perspective. Advances in Complex Systems, 14(3):415–438. URL https://hal-ens-lyon.archives-ouvertes.fr/ ensl-00490325.

Breiman, L. (1996). Bagging predictors. Machine learning, 24(2):123–140. Bussab, W. O. e Morettin, P. A. (2010). Estatística Básica. Saraiva.

Caulfield, B., O’Mahony, M., Brazil, W., e Weldon, P. (2017). Examining usage patterns of a bike- sharing scheme in a medium sized city. Transportation Research Part A: Policy and Practice, 100:152 – 161. ISSN 0965-8564. URL http://www.sciencedirect.com/science/ article/pii/S0965856416304141.

Chen, L. e Jakubowicz, J. (2015). Inferring bike trip patterns from bike sharing system open data.

In 2015 IEEE International Conference on Big Data (Big Data), p. 2898–2900. Chiavenato, I. (2014). Introdução à teoria geral da administração. Editora Manole.

Dupuis, D. J. e Field, C. A. (2004). Large wind speeds: Modeling and outlier detection. Journal of Agricultural, Biological, and Environmental Statistics, 9(1):105–121. ISSN 10857117. URL http://www.jstor.org/stable/1400709.

Fishman, E., Washington, S., Haworth, N., e Watson, A. (2015). Factors influencing bike share membership: An analysis of melbourne and brisbane. Transportation Research Part A: Policy and Practice, 71:17 – 30. ISSN 0965-8564. URL http://www.sciencedirect.com/ science/article/pii/S0965856414002638.

Georgescu, M., Pavaloaia, V., Popescul, D., e Tugui, A. (2015). The race for making up the list of emergent smart cities. an eastern european country’s approach. Transformations in Business and Economics, 14:529–549.

James, G., Witten, D., Hastie, T., e Tibshirani, R. (2013). An Introduction to Statistical Learning with Applications in R. Springer Texts in Statistics. Springer.

Kaltenbrunner, A., Meza, R., Grivolla, J., Codina, J., e Banchs, R. (2010). Urban cycles and mobility patterns: Exploring and predicting trends in a bicycle-based public transport system. Pervasive and Mobile Computing, 6(4):455 – 466. ISSN 1574-1192. URL http:// www.sciencedirect.com/science/article/pii/S1574119210000568. Human Behavior in Ubiquitous Environments: Modeling of Human Mobility Patterns.

Kuncheva, L. I. (2014). Combining Pattern Classifiers: Methods and Algorithms. Wiley Publishing, 2nd edition. ISBN 1118315235.

Liu, J., Sun, L., Chen, W., e Xiong, H. (2016). Rebalancing bike sharing systems: A multi-source data smart optimization. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD ’16, p. 1005–1014, New York, NY, USA. Association for Computing Machinery. ISBN 9781450342322. URL https://doi.org/ 10.1145/2939672.2939776.

Mahmoud, M., El-Assi, W., e Nurul Habib, K. (2015). Effects of built environment and weather on bike sharing demand: Station level analysis of commercial bike sharing in toronto.

Moncayo-Martínez, L. A. e Ramirez-Nafarrate, A. (2016). Visualization of the mobility patterns in the bike-sharing transport systems in mexico city. In 2016 IEEE International Conference on Industrial Engineering and Engineering Management (IEEM), p. 1851–1855.

Mossa, R. V., Ladewig, I., e Uvinha, R. R. (2020). Desafios da bicicleta como meio de transporte: o deslocamento de estudantes de dois colégios da rede pública no viário de curitiba. Brazilian Journal of Development, 6(6):33485–33505.

O’Mahony, E. e Shmoys, D. B. (2015). Data analysis and optimization for (citi)bike sharing. In Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence, AAAI’15, p. 687–694. AAAI Press. ISBN 0262511290.

Pasquale, P., Neto, C., Gomes, e Celso (2011). Comunicação Integrada de Marketing: A Teoria na Prática. Elsevier.

Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., e Duchesnay, E. (2011). Scikit-learn: Machine learning in Python. Journal of Ma chine Learning Research, 12:2825–2830.

Randhawa, A. e Kumar, A. (2017). Exploring sustainability of smart development initiatives in india. International Journal of Sustainable Built Environment, 6(2):701 – 710. ISSN 2212-6090. URL http://www.sciencedirect.com/science/article/ pii/S2212609017300742.

Shlens, J. (2014). A tutorial on principal component analysis. CoRR, abs/1404.1100. URL http:

//arxiv.org/abs/1404.1100.

Tang, J., Alelyani, S., e Liu., H. (2015). Data Classification: Algorithms and Applications. Data Mining and Knowledge Discovery Series, CRC Press.

Viana, J. D. F., Gurgel, T. K. S., Chaves e Silva, L., Alves Filho, S. E., e Liberalino, C. H. P. (2020). Análise comparativa de modelos preditivos na gestão estratégica de bicicletas compartilhadas: Um estudo de caso. In Anais do LII Simpósio Brasileiro de Pesquisa Operacional - SBPO. Sociedade Brasileira de Computação (SBC). URL https://proceedings.science/sbpo-2020/papers/

analise-comparativa-de-modelos-preditivos-na-gestao-estrategica-de-bicicleta

Viana, J. D. F., Braga, O., Silva, L., e Neto, F. M. (2019). Analyzing patterns of a bicycle sharing system for generating rental flow predictive models. In Anais do III Workshop de Computação Urbana, p. 57–70, Porto Alegre, RS, Brasil. SBC. URL https://sol.sbc.org.br/ index.php/courb/article/view/7468.

Vogel, P., Greiser, T., e Mattfeld, D. C. (2011). Understanding bike-sharing systems using data mining: Exploring activity patterns. Procedia - Social and Behavioral Sciences, 20:514 –

ISSN 1877-0428. URL http://www.sciencedirect.com/science/article/ pii/S1877042811014388. The State of the Art in the European Quantitative Oriented Transportation and Logistics Research – 14th Euro Working Group on Transportation & 26th Mini Euro Conference & 1st European Scientific Conference on Air Transport.

Wikipedia (2020). Washington, D.C. Online: https://pt.wikipedia.org/wiki/ Washington,_D.C. Acessado em 30/10/2020.

Xu, T., Han, G., Qi, X., Du, J., Lin, C., e Shu, L. (2020). A hybrid machine learning model for demand prediction of edge-computing-based bike-sharing system using internet of things. IEEE Internet of Things Journal, 7(8):7345–7356.

Zhang, L., Zhang, J., yu Duan, Z., e Bryde, D. (2015). Sustainable bike-sharing systems: characteristics and commonalities across cases in urban china. Journal of Cleaner Production, 97:124 –

ISSN 0959-6526. URL http://www.sciencedirect.com/science/article/ pii/S0959652614003448. Special Volume: Why have ‘Sustainable Product-Service Systems’ not been widely implemented?

Zhang, Y. e Mi, Z. (2018). Environmental benefits of bike sharing: A big data-based analysis. Applied Energy, 220:296 – 301. ISSN 0306-2619. URL http://www.sciencedirect. com/science/article/pii/S0306261918304392.




DOI: https://doi.org/10.34117/bjdv7n1-151

Refbacks

  • There are currently no refbacks.