Airbnb rental price modeling based on Latent Dirichlet Allocation and MESF-XGBoost composite model

Airbnb price modeling is an important decision-making tool that determines the acceptability and profitability of the service. In this study, we demonstrated how proper descriptions of an Airbnb listing and location could influence determining the prices. We assumed the proper description of a listi...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Md Didarul Islam, Bin Li, Kazi Saiful Islam, Rakibul Ahasan, Md. Rimu Mia, Md Emdadul Haque
Formato:	article
Lenguaje:	EN
Publicado:	Elsevier 2022
Materias:	Machine Learning Latent Dirichlet Allocation Eigenvector Spatial Filtering XGBoost Spatial Data Modeling Cybernetics Q300-390 Electronic computers. Computer science QA75.5-76.95
Acceso en línea:	https://doaj.org/article/2b79665204014de6b426f581ab48584b
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:2b79665204014de6b426f581ab48584b
record_format	dspace
spelling	oai:doaj.org-article:2b79665204014de6b426f581ab48584b2021-11-30T04:17:54ZAirbnb rental price modeling based on Latent Dirichlet Allocation and MESF-XGBoost composite model2666-827010.1016/j.mlwa.2021.100208https://doaj.org/article/2b79665204014de6b426f581ab48584b2022-03-01T00:00:00Zhttp://www.sciencedirect.com/science/article/pii/S2666827021001043https://doaj.org/toc/2666-8270Airbnb price modeling is an important decision-making tool that determines the acceptability and profitability of the service. In this study, we demonstrated how proper descriptions of an Airbnb listing and location could influence determining the prices. We assumed the proper description of a listing property positively influences the renter’s decision making; therefore, we applied a Latent Dirichlet Allocation (LDA) based topic model for generating synthetic variables from the textual description of property aiming to improve price prediction accuracy. Additionally, we applied a Moran Eigenvector Spatial Filtering based XGBoost (MESF-XGBoost) model to address the spatial dependence of location data and improve prediction accuracy. Our study at the San Jose County Airbnb dataset found that the number of bedrooms, accommodations, property types, and the total number of reviews positively influence the listing price, whereas the absence of a super host badge and cancellation policy negatively influence the price. The experiment demonstrates that incorporating synthetic variables from both LDA and MESF into the model specification improves the prediction accuracy. The experiment reveals that the XGBoost model with only non-spatial features is not strong enough to address spatial dependence; therefore, it cannot minimize spatial autocorrelation issues.Md Didarul IslamBin LiKazi Saiful IslamRakibul AhasanMd. Rimu MiaMd Emdadul HaqueElsevierarticleMachine LearningLatent Dirichlet AllocationEigenvector Spatial FilteringXGBoostSpatial Data ModelingCyberneticsQ300-390Electronic computers. Computer scienceQA75.5-76.95ENMachine Learning with Applications, Vol 7, Iss , Pp 100208- (2022)
institution	DOAJ
collection	DOAJ
language	EN
topic	Machine Learning Latent Dirichlet Allocation Eigenvector Spatial Filtering XGBoost Spatial Data Modeling Cybernetics Q300-390 Electronic computers. Computer science QA75.5-76.95
spellingShingle	Machine Learning Latent Dirichlet Allocation Eigenvector Spatial Filtering XGBoost Spatial Data Modeling Cybernetics Q300-390 Electronic computers. Computer science QA75.5-76.95 Md Didarul Islam Bin Li Kazi Saiful Islam Rakibul Ahasan Md. Rimu Mia Md Emdadul Haque Airbnb rental price modeling based on Latent Dirichlet Allocation and MESF-XGBoost composite model
description	Airbnb price modeling is an important decision-making tool that determines the acceptability and profitability of the service. In this study, we demonstrated how proper descriptions of an Airbnb listing and location could influence determining the prices. We assumed the proper description of a listing property positively influences the renter’s decision making; therefore, we applied a Latent Dirichlet Allocation (LDA) based topic model for generating synthetic variables from the textual description of property aiming to improve price prediction accuracy. Additionally, we applied a Moran Eigenvector Spatial Filtering based XGBoost (MESF-XGBoost) model to address the spatial dependence of location data and improve prediction accuracy. Our study at the San Jose County Airbnb dataset found that the number of bedrooms, accommodations, property types, and the total number of reviews positively influence the listing price, whereas the absence of a super host badge and cancellation policy negatively influence the price. The experiment demonstrates that incorporating synthetic variables from both LDA and MESF into the model specification improves the prediction accuracy. The experiment reveals that the XGBoost model with only non-spatial features is not strong enough to address spatial dependence; therefore, it cannot minimize spatial autocorrelation issues.
format	article
author	Md Didarul Islam Bin Li Kazi Saiful Islam Rakibul Ahasan Md. Rimu Mia Md Emdadul Haque
author_facet	Md Didarul Islam Bin Li Kazi Saiful Islam Rakibul Ahasan Md. Rimu Mia Md Emdadul Haque
author_sort	Md Didarul Islam
title	Airbnb rental price modeling based on Latent Dirichlet Allocation and MESF-XGBoost composite model
title_short	Airbnb rental price modeling based on Latent Dirichlet Allocation and MESF-XGBoost composite model
title_full	Airbnb rental price modeling based on Latent Dirichlet Allocation and MESF-XGBoost composite model
title_fullStr	Airbnb rental price modeling based on Latent Dirichlet Allocation and MESF-XGBoost composite model
title_full_unstemmed	Airbnb rental price modeling based on Latent Dirichlet Allocation and MESF-XGBoost composite model
title_sort	airbnb rental price modeling based on latent dirichlet allocation and mesf-xgboost composite model
publisher	Elsevier
publishDate	2022
url	https://doaj.org/article/2b79665204014de6b426f581ab48584b
work_keys_str_mv	AT mddidarulislam airbnbrentalpricemodelingbasedonlatentdirichletallocationandmesfxgboostcompositemodel AT binli airbnbrentalpricemodelingbasedonlatentdirichletallocationandmesfxgboostcompositemodel AT kazisaifulislam airbnbrentalpricemodelingbasedonlatentdirichletallocationandmesfxgboostcompositemodel AT rakibulahasan airbnbrentalpricemodelingbasedonlatentdirichletallocationandmesfxgboostcompositemodel AT mdrimumia airbnbrentalpricemodelingbasedonlatentdirichletallocationandmesfxgboostcompositemodel AT mdemdadulhaque airbnbrentalpricemodelingbasedonlatentdirichletallocationandmesfxgboostcompositemodel
_version_	1718406734342520832

Airbnb rental price modeling based on Latent Dirichlet Allocation and MESF-XGBoost composite model

Ejemplares similares