Data Analysis and Regression Modelling on a Bike Share System

Fitzgerald, Peter (2014) Data Analysis and Regression Modelling on a Bike Share System. Diploma thesis, Dublin, National College of Ireland.

PDF (Diploma)
Download (2MB) | Preview


The purpose of this study was to undertake a statistical analysis of a data set taken from a bike sharing scheme and provide a step by step guide to understanding the different variables within the dataset. The analysis looked at the variables, individually, and then looked at how they interacted with each other. The main aim of the study was to a create a multiple linear regression model that would predict the number of bikes that should be made available at any given hour of the day given a certain set of weather conditions, which would act as the models input variables.

The data comes from a bike sharing system, giving an hourly count of bikes rented over a two year period; these systems have gained increasing support, especially in the last several years. As their popularity grows so does their relevance, and the need to study such systems, as to their validity, becomes ever more important.

The programming language R was used to build the linear regression model, with the end goal of predicting the count of bikes that should be available, given a certain set of weather conditions. The data set was divided into two parts, by year. The first year 2011 was used as the information to build the model and the actual output of 2012 was compared against the predicted results. The results from the model’s predictions varied in success, some predictions were extremely close to the actual count; however there were a number of large differences between the predicted count and the actual count.

The model that was developed predicted well in places but more investigation is required to improve the predictions to a more accurate level.

Item Type: Thesis (Diploma)
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
Divisions: School of Computing > Higher Diploma in Science in Data Analytics
Date Deposited: 16 Dec 2014 14:23
Last Modified: 16 Dec 2014 14:24

Actions (login required)

View Item View Item