Subjective Functionality and Comfort Prediction for Apartment Floor Plans and Its Application to Intuitive Online Property Search

Abstract

This paper presents a new user experience for online apartment search using functionality and comfort as query items. Specifically, it 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 is the first work to propose a highly accurate machine learning model for predicting the subjective functionality and comfort of apartments.

Spatial Analytics of Housing Prices With User-Generated POI Data, a Case Study in Shenzhen

“…This paper aims to investigate the contribution and influence of user-generated POIbased data as indicators (i.e., input variables) for housing price prediction. We present price prediction models using machine learning, which have been widely used in prediction models, for examples, in indoor (Narahara et al, 2022) and urban conditions (Xu et al, 2022). This paper focuses on prediction using support vector regression (SVR), a learning machine that estimates a function given a dataset.…”

Attractiveness Computing in Image Media

“…Figure 1 shows some representative works on attractivenss computing [19]- [30]: presentation analysis, advertisement analysis, enhancing popularity in social network services (SNSs), marketing and promotion, recommendation and matching, real-estate technology, and so forth.…”

“…Apartment Floor Plans Another application of "attractiveness computing" is the very subjective prediction of functionality and comfort for apartment floor plans [30] (Fig, 7). We created and analyzed a large-scale dataset based on subjective evaluation of real estate floor plan images using crowd-sourcing.…”

AI Tools to Synthesize Characteristics of Public Spaces

“…Some technical frameworks demonstrate some premises for evaluating subjective values in public spaces using virtual models (Narahara 2022), multimodal deep neural networks for predicting subjective values in residential apartment floor plans, such as the comfort of living and modernity (Narahara et al, 2022), and the application of machine learning to predict housing prices from street-view perceptions (Xu et al, 2022).…”