Oriental Journal of Computer Science and Technology

Open Access Open Access  Restricted Access Subscription Access

Prediction of Bike Sharing Demand


Affiliations
1 Department of Computer Science, Christ University, Bangalore, 560034, India
 

Bike sharing systems have been gaining prominence all over the world with more than 500 successful systems being deployed in major cities like New York, Washington, London. With an increasing awareness of the harms of fossil based mean of transportation, problems of traffic congestion in cities and increasing health consciousness in urban areas, citizens are adopting bike sharing systems with zest. Even developing countries like India are adopting the trend with a bike sharing system in the pipeline for Karnataka. This paper tackles the problem of predicting the number of bikes which will be rented at any given hour in a given city, henceforth referred to as the problem of ‘Bike Sharing Demand’. In this vein, this paper investigates the efficacy of standard machine learning techniques namely SVM, Regression, Random Forests, Boosting by implementing and analyzing their performance with respect to each other.This paper also presents two novel methods, Linear Combination and Discriminating Linear Combination, for the ‘Bike Sharing Demand’ problem which supersede the aforementioned techniques as good estimates in the real world.

Keywords

Learning, Neural Networks, Random Forests, Regression, SVM, Gradient Boosting, Boost, Linear Combination, Python, Weak Learner, Strong Learner.
User
Notifications
Font Size

  • Shaheen, Susan, Stacey Guzman, and Hua Zhang. “Bikesharing in Europe, the Americas, and Asia: past, present, and future.” Transportation Research Record: Journal of the Transportation Research Board 21(43): 159-167, (2010)

  • https://archive.ics.uci.edu/ml/datasets/Bike+Sharing+Data set

  • Kotsiantis, Sotiris B., I. Zaharakis, and P. Pintelas. “Supervised machine learning: A review of classification techniques.” (2007): 3-24.

  • Corinna Cortes and Vladimir Vapnik. Support-vector networks. Machine learning,20(3):273297, 1995.

  • Scholkopf, Bernhard, and Alexander J. Smola. Learning with kernels:support vector machines, regularization, optimization, and beyond. MIT press, 2001.

  • Funahashi, Ken-Ichi. “On the approximate realization of continuous mappings by neural networks.” Neural networks 2.3 (1989): 183-192.

  • Leo Breiman. Random forests. Machine learning, 45(1):532, 2001.

  • Geurts, Pierre, Damien Ernst, and Louis Wehenkel. “Extremely randomized trees.” Machine learning 63.1 (2006): 3-42.

  • Jerome H Friedman. Stochastic gradient boosting. Computational Statistics and Data Analysis, 38(4):367378, 2002.

  • Armstrong, J. Scott, and Fred Collopy. “Error measures for generalizing about forecasting methods: Empirical comparisons.” International journal of forecasting 8.1 (1992): 69-80.

  • Fodor, Imola K. “A survey of dimension reduction techniques.” Center for Applied Scientific Computing, Lawrence Livermore National Laboratory 9 (2002): 1-18

  • Jolliffe, Ian. Principal component analysis. John Wiley and Sons, Ltd, 2002.

  • Somers, A., and H. Eldaly. “Is Australia ready for Mobility as a Service?.” ARRB Conference, 27th, 2016, Melbourne, Victoria, Australia. 2016.

  • Verbruggen, K. J. P. Shared cycling infrastructure as a feeder system for public transport in Sao Paulo. BS thesis. University of Twente, 2017.

  • Chen, Mengwei, et al. “Public Bicycle Service Evaluation from Users’ Perspective: Case Study of Hangzhou, China.” Transportation Research Board 96th Annual Meeting. No. 17-04234. 2017.

  • Raviv, Tal, and Ofer Kolka. “Optimal inventory management of a bike-sharing station.” IIE Transactions 45.10 (2013): 1077-1093.


Abstract Views: 209

PDF Views: 4




  • Prediction of Bike Sharing Demand

Abstract Views: 209  |  PDF Views: 4

Authors

Purnima Sachdeva
Department of Computer Science, Christ University, Bangalore, 560034, India
K. N. Sarvanan
Department of Computer Science, Christ University, Bangalore, 560034, India

Abstract


Bike sharing systems have been gaining prominence all over the world with more than 500 successful systems being deployed in major cities like New York, Washington, London. With an increasing awareness of the harms of fossil based mean of transportation, problems of traffic congestion in cities and increasing health consciousness in urban areas, citizens are adopting bike sharing systems with zest. Even developing countries like India are adopting the trend with a bike sharing system in the pipeline for Karnataka. This paper tackles the problem of predicting the number of bikes which will be rented at any given hour in a given city, henceforth referred to as the problem of ‘Bike Sharing Demand’. In this vein, this paper investigates the efficacy of standard machine learning techniques namely SVM, Regression, Random Forests, Boosting by implementing and analyzing their performance with respect to each other.This paper also presents two novel methods, Linear Combination and Discriminating Linear Combination, for the ‘Bike Sharing Demand’ problem which supersede the aforementioned techniques as good estimates in the real world.

Keywords


Learning, Neural Networks, Random Forests, Regression, SVM, Gradient Boosting, Boost, Linear Combination, Python, Weak Learner, Strong Learner.

References





DOI: https://doi.org/10.13005/ojcst%2F10.01.30