Scalable Prediction Models for Airbnb Listing in Spark Big Data Cluster using GPU-accelerated RAPIDS

Samyuktha Muralidharan; Savita Yadav; Jungwoo Huh; Sanghoon Lee; Jongwook Woo

doi:10.6109/jicce.2022.20.2.96

Scalable Prediction Models for Airbnb Listing in Spark Big Data Cluster using GPU-accelerated RAPIDS

Samyuktha Muralidharan, Savita Yadav, Jungwoo Huh, Sanghoon Lee, Jongwook Woo

Department of Electrical and Electronic Engineering

Research output: Contribution to journal › Article › peer-review

Abstract

We aim to build predictive models for Airbnb’s prices using a GPU-accelerated RAPIDS in a big data cluster. The Airbnb Listings datasets are used for the predictive analysis. Several machine-learning algorithms have been adopted to build models that predict the price of Airbnb listings. We compare the results of traditional and big data approaches to machine learning for price prediction and discuss the performance of the models. We built big data models using Databricks Spark Cluster, a distributed parallel computing system. Furthermore, we implemented models using multiple GPUs using RAPIDS in the spark cluster. The model was developed using the XGBoost algorithm, whereas other models were developed using traditional central processing unit (CPU)-based algorithms. This study compared all models in terms of accuracy metrics and computing time. We observed that the XGBoost model with RAPIDS using GPUs had the highest accuracy and computing time.

Original language	English
Pages (from-to)	96-102
Number of pages	7
Journal	Journal of Information and Communication Convergence Engineering
Volume	20
Issue number	2
DOIs	https://doi.org/10.6109/jicce.2022.20.2.96
Publication status	Published - 2022

Bibliographical note

Funding Information:
Dr. Woo received his Ph.D. from USC and w ent to Yonsei University. He is a Professor at CIS Department of California State University Los Angeles and serves as a Technical Advisor of Teradata, Spark Technology Center and KSEA-SC. He has consulted companies in Hollyw ood. He has published more than 50 papers regarding Scalable Deep Learning, Big Data Analysis and Prediction. He has been awarded Teradata TUN faculty Scholarship and received grants from Databricks, NVidia, Amazon, IBM, Oracle, Microsoft, Cloudera, Hortonworks, SAS, QlikView, and Tableau.

Funding Information:
The Databrick University Alliance supported this research. We appreciate the support of Rob Reed, Program Director at Databricks University Alliance

Publisher Copyright:
© The Korea Institute of Information and Communication Engineering

All Science Journal Classification (ASJC) codes

Information Systems
Media Technology
Computer Networks and Communications
Electrical and Electronic Engineering

Access to Document

10.6109/jicce.2022.20.2.96

Cite this

@article{e5d5ed38ce124952b16f1cc3563671b5,

title = "Scalable Prediction Models for Airbnb Listing in Spark Big Data Cluster using GPU-accelerated RAPIDS",

abstract = "We aim to build predictive models for Airbnb{\textquoteright}s prices using a GPU-accelerated RAPIDS in a big data cluster. The Airbnb Listings datasets are used for the predictive analysis. Several machine-learning algorithms have been adopted to build models that predict the price of Airbnb listings. We compare the results of traditional and big data approaches to machine learning for price prediction and discuss the performance of the models. We built big data models using Databricks Spark Cluster, a distributed parallel computing system. Furthermore, we implemented models using multiple GPUs using RAPIDS in the spark cluster. The model was developed using the XGBoost algorithm, whereas other models were developed using traditional central processing unit (CPU)-based algorithms. This study compared all models in terms of accuracy metrics and computing time. We observed that the XGBoost model with RAPIDS using GPUs had the highest accuracy and computing time.",

author = "Samyuktha Muralidharan and Savita Yadav and Jungwoo Huh and Sanghoon Lee and Jongwook Woo",

note = "Funding Information: Dr. Woo received his Ph.D. from USC and w ent to Yonsei University. He is a Professor at CIS Department of California State University Los Angeles and serves as a Technical Advisor of Teradata, Spark Technology Center and KSEA-SC. He has consulted companies in Hollyw ood. He has published more than 50 papers regarding Scalable Deep Learning, Big Data Analysis and Prediction. He has been awarded Teradata TUN faculty Scholarship and received grants from Databricks, NVidia, Amazon, IBM, Oracle, Microsoft, Cloudera, Hortonworks, SAS, QlikView, and Tableau. Funding Information: The Databrick University Alliance supported this research. We appreciate the support of Rob Reed, Program Director at Databricks University Alliance Publisher Copyright: {\textcopyright} The Korea Institute of Information and Communication Engineering",

year = "2022",

doi = "10.6109/jicce.2022.20.2.96",

language = "English",

volume = "20",

pages = "96--102",

journal = "Journal of Information and Communication Convergence Engineering",

issn = "2234-8255",

publisher = "The Korean Institute of Information and Commucation Engineering",

number = "2",

}

TY - JOUR

T1 - Scalable Prediction Models for Airbnb Listing in Spark Big Data Cluster using GPU-accelerated RAPIDS

AU - Muralidharan, Samyuktha

AU - Yadav, Savita

AU - Huh, Jungwoo

AU - Lee, Sanghoon

AU - Woo, Jongwook

N1 - Funding Information: Dr. Woo received his Ph.D. from USC and w ent to Yonsei University. He is a Professor at CIS Department of California State University Los Angeles and serves as a Technical Advisor of Teradata, Spark Technology Center and KSEA-SC. He has consulted companies in Hollyw ood. He has published more than 50 papers regarding Scalable Deep Learning, Big Data Analysis and Prediction. He has been awarded Teradata TUN faculty Scholarship and received grants from Databricks, NVidia, Amazon, IBM, Oracle, Microsoft, Cloudera, Hortonworks, SAS, QlikView, and Tableau. Funding Information: The Databrick University Alliance supported this research. We appreciate the support of Rob Reed, Program Director at Databricks University Alliance Publisher Copyright: © The Korea Institute of Information and Communication Engineering

PY - 2022

Y1 - 2022

N2 - We aim to build predictive models for Airbnb’s prices using a GPU-accelerated RAPIDS in a big data cluster. The Airbnb Listings datasets are used for the predictive analysis. Several machine-learning algorithms have been adopted to build models that predict the price of Airbnb listings. We compare the results of traditional and big data approaches to machine learning for price prediction and discuss the performance of the models. We built big data models using Databricks Spark Cluster, a distributed parallel computing system. Furthermore, we implemented models using multiple GPUs using RAPIDS in the spark cluster. The model was developed using the XGBoost algorithm, whereas other models were developed using traditional central processing unit (CPU)-based algorithms. This study compared all models in terms of accuracy metrics and computing time. We observed that the XGBoost model with RAPIDS using GPUs had the highest accuracy and computing time.

AB - We aim to build predictive models for Airbnb’s prices using a GPU-accelerated RAPIDS in a big data cluster. The Airbnb Listings datasets are used for the predictive analysis. Several machine-learning algorithms have been adopted to build models that predict the price of Airbnb listings. We compare the results of traditional and big data approaches to machine learning for price prediction and discuss the performance of the models. We built big data models using Databricks Spark Cluster, a distributed parallel computing system. Furthermore, we implemented models using multiple GPUs using RAPIDS in the spark cluster. The model was developed using the XGBoost algorithm, whereas other models were developed using traditional central processing unit (CPU)-based algorithms. This study compared all models in terms of accuracy metrics and computing time. We observed that the XGBoost model with RAPIDS using GPUs had the highest accuracy and computing time.

UR - http://www.scopus.com/inward/record.url?scp=85134378639&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85134378639&partnerID=8YFLogxK

U2 - 10.6109/jicce.2022.20.2.96

DO - 10.6109/jicce.2022.20.2.96

M3 - Article

AN - SCOPUS:85134378639

SN - 2234-8255

VL - 20

SP - 96

EP - 102

JO - Journal of Information and Communication Convergence Engineering

JF - Journal of Information and Communication Convergence Engineering

IS - 2

ER -

Scalable Prediction Models for Airbnb Listing in Spark Big Data Cluster using GPU-accelerated RAPIDS

Abstract

Bibliographical note

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this