Fuzzy Logic Recommender Model for Housing
Recommending suitable housing implies significant challenges owing to the continuous increase in demand and the need to meet habitability standards. This document presents an innovative approach with which to address these challenges through the use of a housing recommendation method based on distan...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10835103/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Recommending suitable housing implies significant challenges owing to the continuous increase in demand and the need to meet habitability standards. This document presents an innovative approach with which to address these challenges through the use of a housing recommendation method based on distances to key spatial points and the latent characteristics of the properties. The proposed method employs objective distances from the properties to points of interest, such as educational centers, medical centers, pharmacies, shops, entertainment, 911 security cameras and public transport stations. These distances are calculated on the basis of the area in which the property is located, thus providing an accurate assessment of the environment. Moreover, housing features are grouped into three correlated latent factors: Size and Value, Environment and Comfort, and Age and Safety. The recommendation system relies on fuzzy control to manage user preferences and select appropriate input data with which to test the model. A content-based filtering approach is used initially, as housing ratings are unavailable. The model predicts a percentage of membership in each cluster, which makes it possible to handle uncertainty by offering properties from different groups in a proportional manner. Euclidean distance is employed in order to measure the similarity between user preferences and housing characteristics, after which the search time is optimized by utilizing metaheuristic methods, of which the bat algorithm provides the best performance in terms of time. This algorithm selects the properties displayed to the user on the basis of natural features extracted from real estate platforms by means of web scraping techniques. The system is built with a Model-View-Controller architecture using Python, Flask, and SQLite. Personal customer data is also recorded in order to create clusters and calculate distances for new customers, thus allowing properties with high ratings to be recommended. This approach combines collaborative and content-based filtering, creating a hybrid system that improves recommendation accuracy and relevance. This analysis shows that the new recommendation method is an effective and accessible solution with which to select suitable housing. |
|---|---|
| ISSN: | 2169-3536 |