Presentation information

Organized Session

Organized Session » [OS] OS-10

[1D2-OS-10a] 不動産とAI(1)

Tue. Jun 4, 2019 1:20 PM - 3:00 PM Room D (301B Medium meeting room)

清田 陽司((株)LIFULL)、山崎 俊彦(東京大学)、諏訪 博彦(奈良先端科学技術大学院大学)、清水 千弘(日本大学)、橋本 武彦(GA technologies)

2:40 PM - 3:00 PM

[1D2-OS-10a-05] Evaluation of Rent Prediction Models using Floor Plan Images

〇Ryosuke Hattori1, Kazushi Okamoto1, Atsushi Shibata2 (1. The University of Electro-Communications, 2. Advanced Institute of Industrial Technology)

Keywords:rent prediction, floor plan image, principal component analysis, convolutional neural network

This study constructs rent prediction models with/without floor plan images in order to validate whether such images contribute the prediction accuracy. In addition, applications of PCA (principal component analysis) and convolutional neural network are considered as a feature extractor from floor plan images. The prediction accuracy is measured using properties of 90,000 rental housings in Tokyo. In the experimental results, the root mean squared error values of the prediction model with floor plan images and PCA tend to be higher than without floor plan images. This suggests that the use of floor plan images contributes to accuracy of rent prediction.