Subjective Functionality and Comfort Prediction for Apartment Floor Plans and Its Application to Intuitive Searches

TL;DR

This paper introduces a novel approach to apartment search by predicting subjective functionality and comfort from floor plans using machine learning, enhancing user experience through a new dataset, prediction algorithm, and a usability study.

Contribution

It presents the first highly accurate machine learning model for subjective apartment functionality and comfort prediction from floor plans, along with a new dataset and a user-centric search system.

Findings

The search system improves user experience.

High accuracy in predicting comfort and functionality scores.

Successful large-scale usability validation.

Abstract

This study presents a new user experience in apartment searches using functionality and comfort as query items. This study has three technical contributions. First, we present a new dataset on the perceived functionality and comfort scores of residential floor plans using nine question statements about the level of comfort, openness, privacy, etc. Second, we propose an algorithm to predict the scores from the floor plan images. Lastly, we implement a new apartment search system and conduct a large-scale usability study using crowdsourcing. The experimental results show that our apartment search system can provide a better user experience. To the best of our knowledge, this study is the first work to propose a highly accurate prediction model for the subjective functionality and comfort of apartments using machine learning.