Foyer, Inc., a startup PropTech development company, introduces Foyer Insight, the most advanced computer vision Artificial Intelligence (AI) suite focused solely on the real estate industry.
Using multi-label image classification and unsupervised learning, Foyer Insight gives real estate agents tools to be more responsive to client needs by enabling them to put a more verified image first solution at the fingertips of a new generation of home buyers, thereby elevating and streamlining the home buying process.
Built on over 400 million listing images, the system uses proprietary unsupervised learning to analyse images for every listing in the country. It combines the results with listing text and property data to uncover practical guidance to understand and improve listing effectiveness. It also allows for fully customisable models based on individual real estate companies’ specifications.
Foyer Insight also powers the company’s visual suite which includes: Foyer Overview, a real estate company portal offering the most robust imagery management system utilising classification, object detection and validation; Foyer Envision, the live listing input application that gives agents the ability to quickly and seamlessly enter data from new listings while still in the field rather than waiting to return to their office; and Foyer Home Discovery (HD), a state-of-the-art mobile application that allows potential home buyers to evaluate data-rich images and has their preferences instantly communicated to their real estate agent who then receives custom recommendations for each client.
Read More: The AI Trends for 2021
According to a recent study by the National Association of Realtors, 44% of buyers began their home buying process by looking online. Over 92 per cent of buyers used the internet at some point in the process.
And among buyers who used the internet during their home search, 87% found photos and 85% found detailed information about the properties for sale extremely useful.
Foyer Insight is built to gain a wealth of knowledge and data from images within real estate listings. Instead of the agent or broker performing the tedious, time-consuming task of manually entering critical property information such as several rooms or layouts as well as amenities and features, the images can now be sent through the Foyer Insight API, where the system identifies and classifies types of rooms, objects, text, scenes, and image quality.
Foyer Insight also validates that the images uploaded meet the standards set by each real estate company in terms of quality and content. With speeds of approximately 350ms per image and an industry-leading accuracy rating of over 98 per cent, this deep learning technology is highly scalable and reliable. It can be seamlessly integrated with the realty company’s existing functionality.
“While there is increasingly widespread recognition and a growing acceptance of PropTech’s potential, the real estate industry has historically been slow to adapt to changing technologies,” said Robert Cowan, Chief Revenue Officer at Foyer.
“With unsupervised learning as the foundation, Foyer Insight evens the playing field for real estate agents and enables them to offer clients a more robust home buying experience.”
“It is a simpler, more intuitive interface backed by powerful tools, including big data and machine learning, that connect and empower the market of agents and potential home buyers.”
“Unsupervised learning’s impact on data cannot be underestimated, especially in the real estate industry,” said Andrew Sidhu, Foyer CEO.
“Real estate imagery is subjective in general and can vary greatly by cultures, regions, or even neighbourhoods. The only way to be consistent in all cases is to eliminate human biases by the people building the model.”
“Removing the bias and combining it with Foyer’s ability to work off millions of images, means it isn’t overfitted to a certain décor. This allows it to be easily scalable to other markets and perform at an equivalent level anywhere its deployed.”
Read More: Top trends in Natural Language Processing.
“The adaptable nature of unsupervised learning means it can be used for any model training, but it is perfect for real estate because the classifications are not cut and dry, or mutually exclusive in nature,” said Sidhu.
“In the past, it has been difficult to deal with edge cases using supervised learning. But now using unsupervised learning, the model grows on its own and develops its own consensus.”
“Additionally, with unsupervised learning, we can scale new features into production much more efficiently, without the need to hand feed large amounts of data. With Foyer’s unique model training, the models actually build out the features on their own rather than requiring our developers and client partners to walk it through every step.”
“This new real estate technology is not intended to replace the real estate agent. The number of buyers that purchased their home through an agent or broker has increased by almost 20% over the last twenty years.”
“In fact, the human connection between the agent or broker and the home buyer is still one of the most important elements of the real estate transaction. This is why Foyer believes it is so important to put the most advanced technology into the agents’ hands.”
“Through the use of AI and machine learning, Foyer Insight makes the data collected more actionable, and helps agents enhance and improve their clients’ experiences during the home buying process,” said Cowan.
Until now, property search sites usually relied on simple preferences such as location and price to display sale properties. Combining big data and AI, Foyer Insight allows real estate agents to provide interfaces that allow clients to search photos and information based on room type, lighting, specific features (hardwood floors, stainless steel appliances), and more.
Foyer also allows realty search sites to evaluate pricing trends and neighbourhood services such as transportation and schools.
Foyer, Inc., is a PropTech development company whose mission is to help the U.S. real estate industry evolve the home buying process using more innovative and intuitive tools to help real estate agents and home buyers.
Headquartered in Trumbull, CT, Foyer’s elite team of AI developers have pushed unsupervised machine learning and multi-classification tools to a new level. For more information, visit www.foyer.ai.
