Clustering helps to improve price prediction in online booking systems
International Journal of Web Information Systems
ISSN: 1744-0084
Article publication date: 8 January 2021
Issue publication date: 23 January 2021
Abstract
Purpose
Pricing on the online booking systems is a difficult task for the host, the systems usually set the prices that are lower than the general premises and quality, and that only gives benefits to the system by easily attracting the customer to use the service. The setting price of the new accommodation is often based on location, the number of beds, type of house and so on. The main problem is to predict the most reasonable price for the host. This paper aims to study the use of machine learning and sentiment analysis for predicting the price of online booking systems.
Design/methodology/approach
In particular, an empirical study is performed first for some well-known classification models for the problems. The authors then propose to apply k-means, a clustering technique, together with Gradient Boost and XGBoost models to improve the prediction performance. Experiments are conducted and tested for real Airbnb data sets collected in London City.
Findings
Experimental results are given and compared to show that the authors’ method outperforms to an updated method.
Originality/value
The authors use k-means and sampling together with Gradient Boost and XGBoost models to improve the prediction performance.
Keywords
Acknowledgements
This research is funded by Vietnam National University Ho Chi Minh City (VNU-HCM) under grant number C2019-20–13.
A part of the paper was written in the Advanced Computing Lab (AC-Lab), Ho Chi Minh City University of Technology, VNU-HCM. The authors would like to thank Prof Tran Khanh Dang for his comments to improving the final version of the paper.
Citation
Trang, L.H., Huy, T.D. and Le, A.N. (2021), "Clustering helps to improve price prediction in online booking systems", International Journal of Web Information Systems, Vol. 17 No. 1, pp. 45-53. https://doi.org/10.1108/IJWIS-11-2020-0065
Publisher
:Emerald Publishing Limited
Copyright © 2020, Emerald Publishing Limited