Construction of Rent Estimation Model for Restaurants Using Doc2Vec
-
- TSURUYAMA Yukiko
- Nara Institute of Science and Technology
-
- SUWA Hirohiko
- Nara Institute of Science and Technology
-
- OGAWA Yuki
- Ritsumeikan University
-
- ARAKAWA Yutaka
- Nara Institute of Science and Technology
-
- YASUMOTO Keiichi
- Nara Institute of Science and Technology
Bibliographic Information
- Other Title
-
- Doc2Vecを用いた飲食店向け不動産店舗賃料推定モデルの構築
Abstract
<p>The rent for restaurants is determined based on tacit knowledge such as experience and intuition cultivated by veteran sales man of real estate companies. Determinants of the rent include static information that is specific to the property, dynamic information that is around the property, potential information that include features of the property. Potential information is difficult to index by veteran sales man. In this research, we propose a method using catch phrase given to property as potential information. We use the catch phrase that was vectorized by Doc2Vec, and in order to remove noise, we selected part of speech. As a result, the estimation accuracy was higher to select part of speech, and when multiple regression analysis was used, the highest coefficient of determination 0.611 was obtained.</p>
Journal
-
- JSAI Technical Report, Type 2 SIG
-
JSAI Technical Report, Type 2 SIG 2019 (SAI-034), 03-, 2019-03-07
The Japanese Society for Artificial Intelligence
- Tweet
Details 詳細情報について
-
- CRID
- 1390289225021791360
-
- NII Article ID
- 130008081674
-
- ISSN
- 24365556
-
- Text Lang
- ja
-
- Data Source
-
- JaLC
- CiNii Articles
-
- Abstract License Flag
- Allowed