Analyzing Bike Purchase Predictions Using Machine Learning

Yuzhe Zhang

2024

Abstract

As environmental awareness and the promotion of healthy lifestyles continue to rise globally, understanding the determinants of consumer decisions regarding bicycle purchases has become increasingly important. Using four machine learning models - Random Forest (RF), Decision Tree (DT), eXtreme Gradient Boosting (XGBoost), and Logistic Regression (LR) - this study examines the variables influencing bicycle buying behavior. The experimental results demonstrate that age, income, and car ownership consistently emerged as significant predictors of bicycle purchasing behavior across all models. Among these, RF and XGBoost exhibited the best performance in predicting bicycle purchases, with higher accuracy and robustness. The findings contribute to both theoretical advancements and practical applications, offering valuable insights for businesses and policymakers aiming to promote cycling as a sustainable mode of transportation. Furthermore, this study provides a comprehensive framework for understanding the key factors driving consumer decisions, suggesting that future research should explore hybrid models and additional socioeconomic and cultural variables for more accurate predictions.

Paper Citation

in Harvard Style

Zhang Y. (2024). Analyzing Bike Purchase Predictions Using Machine Learning. In Proceedings of the 1st International Conference on E-commerce and Artificial Intelligence - Volume 1: ECAI; ISBN 978-989-758-726-9, SciTePress, pages 274-279. DOI: 10.5220/0013214700004568

in Bibtex Style

@conference{ecai24,
author={Yuzhe Zhang},
title={Analyzing Bike Purchase Predictions Using Machine Learning},
booktitle={Proceedings of the 1st International Conference on E-commerce and Artificial Intelligence - Volume 1: ECAI},
year={2024},
pages={274-279},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013214700004568},
isbn={978-989-758-726-9},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on E-commerce and Artificial Intelligence - Volume 1: ECAI
TI - Analyzing Bike Purchase Predictions Using Machine Learning
SN - 978-989-758-726-9
AU - Zhang Y.
PY - 2024
SP - 274
EP - 279
DO - 10.5220/0013214700004568
PB - SciTePress