A recent newsletter from Peter Diamandis’ Abundance Insider inspired the writing of this article. If you are an entrepreneur and you aren’t familiar with Peter, I highly recommend you check him out. You have likely heard of some of his ventures like the XPRIZE and Zero-G. You can subscribe to his newsletter, Abundance Insider, here.

There seems to be some general confusion around terms like SaaS, PaaS, and newer iterations like MLaaS and AIaaS. Admittedly, for a long time, I didn’t realize there was much of a distinction and grouped all of these under the SaaS umbrella. …


Image for post
Image for post

An AI-powered world is not a futuristic prediction — it is how our society is currently shaping up to be.

From self-driving cars to manufacturing automation, the impact of AI on industries across the world is expected to increase productivity by 40%.

In real estate, artificial intelligence (AI) will lead to a deeper understanding of the market and open up new opportunities for the industry.

AI’s ability to learn and derive insights from the massive deposit of data in the real estate industry will eventually lead us to more efficient agents and brokers, more satisfied clients, and outsized returns for investors. …


Foxy AI Logo
Foxy AI Logo

To kick-off 2020, I thought it would be fun to write an article about a question I get asked all the time, “Where did the name Foxy AI come from?”

Back when Foxy AI was just an idea bubbling in my mind, I was recommended a book called The Signal and the Noise by Nate Silver. In the book, Silver retells the ancient Greek tale of the fox and the hedgehog. The concept of the story is that “The fox knows many little things, but the hedgehog knows one big thing.” Foxes, Silver says, demonstrate predictive skill.

This was the first time I had heard this story, and the idea stuck with me. When making predictions, you want to have many small pieces of information to build the bigger picture. …


Image for post
Image for post
Visual Property Intelligence

Yesterday, I was having a very engaging call with a prospect who brought up something I had never considered before.

We were discussing the use of Foxy AI’s computer vision tools for saving time in her workflow when she mentioned a concept I had not previously considered. That concept is task switching, also known as set-shifting.

The concept states that switching from task A to task B not only incurs a time cost, the time it takes to complete task B, but it also incurs a switch cost.

“This disruption is characterized by a slower performance and decrease in accuracy on a given task A on a trial that follows the performance of a different task B… The difference in accuracy and performance between [the original task] and a task switch (A-B) is known as the switch cost.” …


Image for post
Image for post

We are honored to be selected out of 150 applicants as a finalist for the Global PropTech Awards in the Top Technology Category among so many other leaders and innovators.


Image for post
Image for post

To start, I want to say thank you to all of our customers and partners, especially those of you that have been providing us with invaluable feedback. Your input means a lot to everyone at Foxy AI.

v1.3.1 includes some, likely overdue, updates on our back end. Most importantly, we now support HTTPS calls to the API. This not only keeps all information encrypted but also eliminates mixed content blocking issues with browsers and with Javascript.

If you haven’t already seen it, one of our awesome interns built a fun Chrome extension to utilize our Condition Score application for properties listed on Redfin.com. Now you can quickly score the condition of the property and compare properties in an objective way. …


Foxy AI — Unlock the hidden value of your real estate images
Foxy AI — Unlock the hidden value of your real estate images

Computer vision is on the very edge of changing the home buying experience dramatically. The use of images to help value properties and assist both buyers and investors in searches will help in many ways, especially as the technology matures.

Foxy AI solves a crucial problem in real estate by leveraging new Artificial Intelligence (AI) technology to provide Visual Property Intelligence and unlock the hidden value of your real estate photos.

What is Computer Vision?

Computer vision is training a computer algorithm to interpret and understand images and videos. This technology has been around in some form since the 1950s. …


Image for post
Image for post

An AI-powered world is not a futuristic prediction — it is how our society is currently shaping up to be.

From self-driving cars to manufacturing automation, the impact of AI on industries across the world is expected to increase productivity by 40%.

When it comes to real estate, artificial intelligence (AI) will lead to a deeper understanding of the market and open up new opportunities for the industry.

AI’s ability to learn and derive insights from the massive deposit of data in the real estate industry will eventually lead us to more efficient agents and brokers, more satisfied clients, and outsized returns for investors. …


Image for post
Image for post

Foxy AI has been hard at work forging new partnerships, adding new features, and building feedback loops to continuously improve our existing models.

Several of our customers expressed their need for a more end-to-end solution than what house2vec offered. After much collaboration, we decided boiling house2vec down to a single score, based on Fannie Mae’s quality and condition scoring, would provide the most value to the end user. This score, the “Foxy Condition Score”, is built on the raw data from our proprietary house2vec CNN and input from industry professionals.


Image for post
Image for post

Foxy AI set out to improve residential real estate valuations by incorporating image data. To do this, Foxy AI research developed FoxyNet, the Convolutional Neural Network that powers house2vec. House2vec takes a raw image and returns an image feature vector, embedded in a high dimensional space, containing information on the quality and condition of the property for use in valuation models, among many other applications.

We decided to pair house2vec with arguably the most famous and divisive state of the art valuation model, Zillow’s Zestimate. The results of several experiments will be discussed in a multi-part series.

Step 1: Collect Data

To begin our research, we first collected Zestimates, list prices, and photos for properties listed for sale in Massachusetts. Once we had a robust set of data, we began training a new model. We built this new model by combining the house2vec image feature vector with the Zestimate to produce a new predicted sale price in order to infer whether our embedding space of condition and quality could improve an existing model’s output. …

About

Vin Vomero

Founder & CEO, Foxy AI — Building Visual Property Intelligence

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store