Traffic Prediction of Bike Rental based on Environmental and Seasonal Factors

Ghanbari, Majid (2014) Traffic Prediction of Bike Rental based on Environmental and Seasonal Factors. Diploma thesis, Dublin, National College of Ireland.

PDF (Diploma)
Download (1MB) | Preview


Rental bike systems provide an alternative type of transport to many people. However, it is largely believed that the regular use of them is largely influenced by the environmental factors. People usually blame the bad weather conditions for not getting to work on a bike. The weather conditions and seasonal effect can contribute to the reduction in using these systems while in some cases; the extensive use of them due to good weather conditions could create issues for terrific management authorities in large cities.

In this project, a solution is proposed to model the number of bike users for a rental bike system based on the environmental and seasonal factors. The relationships between environmental variables such as temperature, humidity, wind speed, holidays, weekdays, etc. which can play part in a user’s decision on whether or not to use a bike are investigate. To analyse these variable and their relationships, extensive use of analysis and visualisation tools such as R, Rattle and Weka were used. It is then a linear regression model produced to predict the number of bike users based on weather conditions and seasons and etc.

After performing several tests to determine the quality of the model, it is found that the proposed model can explain around 80% of variations in the target value (number of bike users).

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: 15 Dec 2014 15:10
Last Modified: 15 Dec 2014 15:11

Actions (login required)

View Item View Item