Research on Hotel Reservation Customer Churn Based on Deep Neural Networks

Haoran Sun

2024

Abstract

In recent years, the Internet's rapid development has led to the increasing popularity of various online booking methods. Online hotel booking has emerged as a highly convenient option for individuals to plan their accommodations in advance. However, it is not uncommon to encounter cancellations following reservation confirmations. Hence, predicting the probability of hotel booking cancellations offers significant convenience for both customers and hotel operators,in line with the forecast.To enhance prediction accuracy, this study leverages a range of machine learning techniques and deep learning models, including Logistic Regression (LR), Decision Trees (DT), Random Forest (RF), Gradient Boosting Decision Trees (GBDT), and Deep Neural Networks (DNN). Prior to the experimentation phase, there was an expectation that the DNN model would deliver superior outcomes. The final results validated the exceptional efficiency and effectiveness of the DNN model compared to all other models, achieving an AUC of 0.88 and an accuracy rate of 0.82, positioning it as the leading model among those assessed.

Paper Citation

in Harvard Style

Sun H. (2024). Research on Hotel Reservation Customer Churn Based on Deep Neural Networks. In Proceedings of the 1st International Conference on Engineering Management, Information Technology and Intelligence - Volume 1: EMITI; ISBN 978-989-758-713-9, SciTePress, pages 175-182. DOI: 10.5220/0012918000004508

in Bibtex Style

@conference{emiti24,
author={Haoran Sun},
title={Research on Hotel Reservation Customer Churn Based on Deep Neural Networks},
booktitle={Proceedings of the 1st International Conference on Engineering Management, Information Technology and Intelligence - Volume 1: EMITI},
year={2024},
pages={175-182},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012918000004508},
isbn={978-989-758-713-9},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on Engineering Management, Information Technology and Intelligence - Volume 1: EMITI
TI - Research on Hotel Reservation Customer Churn Based on Deep Neural Networks
SN - 978-989-758-713-9
AU - Sun H.
PY - 2024
SP - 175
EP - 182
DO - 10.5220/0012918000004508
PB - SciTePress