Authors:

Myeongin Wang

Date Created:

Not specified

Course Title:

Professor:

Not specified

About Paper:

In this project, I developed a linear model to predict the number of Seoul's bike-sharing demand. The goal was to identify whether the system would function on a given day by achieving better resource allocation, maintenance planning, and customer service. The prediction is critical for operational efficiency, cost management, and customer satisfaction. The observation includes 365 days from December 2017 to November 2018. The dataset contains various features including, 'rented bike counts', 'hour', 'temperature', 'humidity', etc. Python was the main programming language for this project. For data analysis and visualization purposes, libraries such as Pandas, NumPy, Matplotlib, and Seaborn were used. Three different models - linear regression, ridge regression, and the Lasso - were conducted with 8760 observations and evaluated using 5-fold cross-validation. Model performance will be evaluated based on the adjusted R2 score. Keywords: [no keywords provided]

Source:

Purdue University / 2024

Topics:

No topics listed

Co-authors:

Myeongin Wang