Enhancing Rental Bike Count and Availability Prediction Using Regression Modelling

Abstract

Sharing Bike has become a new concept now a days where one doesn’t have to buy a bike to enjoy their daily ride. Currently it has been introduced in many countries for the betterment of public transportation and other activities. One can rent bikes on several basis like hourly, daily, monthly etc. It has a significant role to the rising issues related to the global warming, climate change, carbon emission and many more environmental anomalies. It is very much necessary to make a system or model which facilitates the availability of rental bikes to the customer at the right time to avoid any delay. In this work, we have used “Linear Regression” and “Polynomial Regression” modelling to predict the rental bike count required at each hour very efficiently. We have used a publicly available dataset of Seoul city, the capital of South Korea containing the rental bike count and other climate related variables. The experimental outcomes of this work shows the efficacy of the proposed method. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.