AIRBNB SINGAPORE LISTING PRICE PREDICTION USING MACHINE LEARNING TECHNIQUES: MULTIPLE LINEAR REGRESSION, RANDOM FOREST, AND GRADIENT BOOSTING
Airbnb, a service company that allows people to rent accommodation to other people has rapidly become one of the biggest trends in the hospitality industry. As a new business model, sharing economy firms are seizing the opportunities, but at the same time, challenged from various perspectives. One o...
Saved in:
| Main Author: | |
|---|---|
| Format: | Final Project |
| Language: | Indonesia |
| Online Access: | https://digilib.itb.ac.id/gdl/view/48932 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Institut Teknologi Bandung |
| Language: | Indonesia |
| id |
id-itb.:48932 |
|---|---|
| spelling |
id-itb.:489322020-08-04T14:54:24ZAIRBNB SINGAPORE LISTING PRICE PREDICTION USING MACHINE LEARNING TECHNIQUES: MULTIPLE LINEAR REGRESSION, RANDOM FOREST, AND GRADIENT BOOSTING Hasanah, Siti Indonesia Final Project Peer-to-Peer Accommodation, Price Prediction, Machine Learning, Multiple Linear Regression, Random Forest, Gradient Boosting INSTITUT TEKNOLOGI BANDUNG https://digilib.itb.ac.id/gdl/view/48932 Airbnb, a service company that allows people to rent accommodation to other people has rapidly become one of the biggest trends in the hospitality industry. As a new business model, sharing economy firms are seizing the opportunities, but at the same time, challenged from various perspectives. One of the important issues in this sharing economy is pricing. Airbnb pricing is crucial to be specified, and the number of listings offered enables this business more competitive and tightening the competition. In the era of the information and communication technology such solutions as big data, business analytics, cloud computing, data mining and business intelligence systems become to play a key role in the process of different organizations' management and one of tools to fix and improve business’ pains. The purpose of this study is to develop and determine price forecasting models of Airbnb listings in Singapore using Machine Learning (Multiple Linear Regression, Random Forest, and Gradient Boosting). This study analyzed 7,676 Singapore Airbnb listings in September 25th, 2019. After processing and analyzing the result, gradient boosting model performed the best with 77.90% model and lowest errors compared to other machine learning models (MSE score 30175679.047, RMSE score 5493.239 with 512 numbers of estimators). The result of this research is expected to help the airbnb hosts solving pricing issue. Keywords: Peer-to-Peer Accommodation, Price Prediction, Machine Learning, Multiple Linear Regression, Random Forest, Gradient Boosting. text |
| institution |
Institut Teknologi Bandung |
| building |
Institut Teknologi Bandung Library |
| continent |
Asia |
| country |
Indonesia Indonesia |
| content_provider |
Institut Teknologi Bandung |
| collection |
Digital ITB |
| language |
Indonesia |
| description |
Airbnb, a service company that allows people to rent accommodation to other people has rapidly become one of the biggest trends in the hospitality industry. As a new business model, sharing economy firms are seizing the opportunities, but at the same time, challenged from various perspectives. One of the important issues in this sharing economy is pricing. Airbnb pricing is crucial to be specified, and the number of listings offered enables this business more competitive and tightening the competition. In the era of the information and communication technology such solutions as big data, business analytics, cloud computing, data mining and business intelligence systems become to play a key role in the process of different organizations' management and one of tools to fix and improve business’ pains. The purpose of this study is to develop and determine price forecasting models of Airbnb listings in Singapore using Machine Learning (Multiple Linear Regression, Random Forest, and Gradient Boosting). This study analyzed 7,676 Singapore Airbnb listings in September 25th, 2019. After processing and analyzing the result, gradient boosting model performed the best with 77.90% model and lowest errors compared to other machine learning models (MSE score 30175679.047, RMSE score 5493.239 with 512 numbers of estimators). The result of this research is expected to help the airbnb hosts solving pricing issue.
Keywords: Peer-to-Peer Accommodation, Price Prediction, Machine Learning, Multiple Linear Regression, Random Forest, Gradient Boosting. |
| format |
Final Project |
| author |
Hasanah, Siti |
| spellingShingle |
Hasanah, Siti AIRBNB SINGAPORE LISTING PRICE PREDICTION USING MACHINE LEARNING TECHNIQUES: MULTIPLE LINEAR REGRESSION, RANDOM FOREST, AND GRADIENT BOOSTING |
| author_facet |
Hasanah, Siti |
| author_sort |
Hasanah, Siti |
| title |
AIRBNB SINGAPORE LISTING PRICE PREDICTION USING MACHINE LEARNING TECHNIQUES: MULTIPLE LINEAR REGRESSION, RANDOM FOREST, AND GRADIENT BOOSTING |
| title_short |
AIRBNB SINGAPORE LISTING PRICE PREDICTION USING MACHINE LEARNING TECHNIQUES: MULTIPLE LINEAR REGRESSION, RANDOM FOREST, AND GRADIENT BOOSTING |
| title_full |
AIRBNB SINGAPORE LISTING PRICE PREDICTION USING MACHINE LEARNING TECHNIQUES: MULTIPLE LINEAR REGRESSION, RANDOM FOREST, AND GRADIENT BOOSTING |
| title_fullStr |
AIRBNB SINGAPORE LISTING PRICE PREDICTION USING MACHINE LEARNING TECHNIQUES: MULTIPLE LINEAR REGRESSION, RANDOM FOREST, AND GRADIENT BOOSTING |
| title_full_unstemmed |
AIRBNB SINGAPORE LISTING PRICE PREDICTION USING MACHINE LEARNING TECHNIQUES: MULTIPLE LINEAR REGRESSION, RANDOM FOREST, AND GRADIENT BOOSTING |
| title_sort |
airbnb singapore listing price prediction using machine learning techniques: multiple linear regression, random forest, and gradient boosting |
| url |
https://digilib.itb.ac.id/gdl/view/48932 |
| _version_ |
1822928038026805248 |