Grant: Alliance Grants
The University of Western Ontario
$24,000.00
Improving digital real estate search and valuation with self-supervised image analysis
FY 2024-25
Summary
Stable housing prices play a key role in supporting economic growth. Real estate valuation (REV) is a process used to determine the monetary value of real estate investments. However, current REV systems do not make use of images of properties, which can contain a wealth of valuable information. Therefore, the development of advanced image-based REV models is crucial for providing more accurate housing prices.
In this proposal, we will address the limitations of REV by developing a series of AI-based models utilizing cutting-edge technologies. The project includes two objectives: Objective 1 (From 2023 to 2024): Creating an AI model for real-time classification of property images as they are uploaded by users on a house search engine; Objective 2 (From 2024 to 2026): Enabling the house search engine to evaluate the similarity and condition of property images, making them searchable for users based on the analysis of similarity or condition scores.
The partner organization is Wahi Ontario Inc. Wahi is a digital real estate platform that allows homeowners and homebuyers to communicate online to conveniently rent or purchase a property. In this project, Wahi will provide real estate images, hold meetings and provide trainees with opportunities for feedback and use the developed AI methods in their online search engine.
This research will add capacity to the Canadian AI industry, and provide opportunities for trainees to hone their
professional skills, such as gaining hands-on industrial experience with AI technology in real-world applications, attending highly prestigious conferences, and fostering open communication between academia and industry. Further, the partner organization will use the proposed methods to provide buyers and sellers with more accurate estimations of what a property is worth. This increased accuracy will help bolster our real estate market and protect the investments of Canadian homeowners.
Program
Alliance Grants
Recipient
Location
Ontario, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data
As published
Application id
583061-2023
Name nom
Yang, Yimin Y
Department département
Electrical and Computer Engineering
Organization id
36
Institution établissement
The University of Western Ontario
Province en
Ontario
Province fr
Ontario
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2024
Competition year année de concours
2023
Award amount
24000
Program id
ALLRP
Program name en
Alliance Grants
Program name fr
Subventions Alliance
Group en
RESEARCH PARTNERSHIPS
Group fr
PARTENARIATS DE RECHERCHE
Committee code
96
Committee name en
RPP Internal Decision Cttee
Committee name fr
Cté de décision interne - PPR
Area of application code
1206
Area of application group en
Advancement of knowledge
Area of application group fr
Avancement des connaissances
Area of application en
Engineering
Area of application fr
Génie
Research subject code
2605
Research subject group en
Robotics
Research subject group fr
Robotique
Research subject en
Pattern analysis and machine intelligence
Research subject fr
Analyse de formes et intelligence artificielle
Field of research list names en
Not available
Field of research list names fr
Non disponible
Socioeconomic objective list names en
Not available
Socioeconomic objective list names fr
Non disponible
Application title
Improving digital real estate search and valuation with self-supervised image analysis
Keywords
deep learning; real estate valuation; representation learning; self-supervised learning
Application summary
Stable housing prices play a key role in supporting economic growth. Real estate valuation (REV) is a process used to determine the monetary value of real estate investments. However, current REV systems do not make use of images of properties, which can contain a wealth of valuable information. Therefore, the development of advanced image-based REV models is crucial for providing more accurate housing prices.
In this proposal, we will address the limitations of REV by developing a series of AI-based models utilizing cutting-edge technologies. The project includes two objectives: Objective 1 (From 2023 to 2024): Creating an AI model for real-time classification of property images as they are uploaded by users on a house search engine; Objective 2 (From 2024 to 2026): Enabling the house search engine to evaluate the similarity and condition of property images, making them searchable for users based on the analysis of similarity or condition scores.
The partner organization is Wahi Ontario Inc. Wahi is a digital real estate platform that allows homeowners and homebuyers to communicate online to conveniently rent or purchase a property. In this project, Wahi will provide real estate images, hold meetings and provide trainees with opportunities for feedback and use the developed AI methods in their online search engine.
This research will add capacity to the Canadian AI industry, and provide opportunities for trainees to hone their
professional skills, such as gaining hands-on industrial experience with AI technology in real-world applications, attending highly prestigious conferences, and fostering open communication between academia and industry. Further, the partner organization will use the proposed methods to provide buyers and sellers with more accurate estimations of what a property is worth. This increased accuracy will help bolster our real estate market and protect the investments of Canadian homeowners.