JSAI Technical Report, Type 2 SIG
Online ISSN : 2436-5556
Construction of Rent Estimation Model for Restaurants Using Doc2Vec
Yukiko TSURUYAMAHirohiko SUWAYuki OGAWAYutaka ARAKAWAKeiichi YASUMOTO
Author information
RESEARCH REPORT / TECHNICAL REPORT FREE ACCESS

2019 Volume 2019 Issue SAI-034 Pages 03-

Details
Abstract

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.

Content from these authors
© 2019 Authors
Previous article Next article
feedback
Top