New level of accuracy for real estate data
Home price valuation is a key part of home selling and buying process. Valuation is also fundamental criteria for banks to make mortgage decision and it is also used in foreclosures.
Automated valuation models (AVM) do not take into account property condition or layout characteristics which can have a major impact on valuation.
CubiCasa real estate data platform has quantified information of property characteristics which enables a totally new level of details and analytics for various real estate use cases.
More information: Jarmo Lumpus, founder & Head of Product, jarmo@cubicasa.com
2. New level of accuracy for real estate data
Home price valuation is key part of home selling and buying
process. Valuation is also fundamental criteria for banks to
make mortgage decision and it is also used in foreclosures.
Automated valuation models (AVM) do not take into account
property condition or layout characteristics which can have
major impact to valuation (https://www.zillow.com/zestimate).
CubiCasa real estate data platform has quantified information
of property characteristics which enables totally new level of
details and analytics for various real estate use cases.
3. CubiCasa property data use cases
1. Fundamental part of the property reports
2. New criterias and features for home search
3. Data for Comparable Market Analysis (CMA)
4. More accurate AVMs (Automated Valuation Models)
5. Find price sensitive factors through data analytics
6. Validate existing real estate data
7. Property characteristics standard through RESO data dictionary
4. CubiCasa property data solution
Convert millions of BIM models with AI tech
+
Automated
conversion
Automated
input acquiring
=
Property Data
Platform
(RESO compliant)
Technology which makes
floor plan input cost
minimal
AI tech to convert BIM
models automatically
Huge amount of property
BIM models accessed
through API
5. What information property BIM model can include?
How many rooms and their type
Size of each room
Number of windows and doors
Kitchen, dining, living room concept
Appliances (e.g. DW)
Terrace/balcony/deck
Bedrooms with W.I.C or en-suite bath
Compass direction
Layout form factor and shape
Special things like: loft, corner apartment, storage
space, ...
CubiCasa solution enables totally new kind of analytics
and finding price sensitive characteristics. There is no
need to ask homeowners to update their property
characteristics, like Zillow and others do.
7. Shorter sales cycle for properties in platform
Property in
platform
Ranks better in
search results
Gets more
views
Shorter
sales cycle
8. All major players provide AVM
● Hometrack acquired by Zoopla for $150M (2017)
● Platinum Data Solutions acquired by Mercury Network (2016)
● FNC acquired by CoreLogic for $475M (2015)
● LPS (BKFS) acquired by Fidelity National $2.9B (2014)
● Retsly acquired by Zillow (2014)
● DataQuick acquired by CoreLogic (2013)
9. Status as of today
>1 million original floor plans
acquired from US
+ =
>95 000 BIM models
converted
> 4500 NYC property BIM
models available in platform
10. How we monetize the property data?
Product
CubiCasa property data platform is accessed only through API
Target segment
Companies providing home search, property report, comparables or AVM
Target market
US
Business model
SaaS
What’s the secret source?
Data reuse: convert once - sell it to many, multiple times!
What other use cases this data enables?
Smart property search for all kinds of real estate apps e.g. AirBnB
11. What this property data is worth?
There is no direct references available but if we look at the property data service
providers
House Canary (www.housecanary.com), the main service being the value report
This company raised $33M A-round Jan 2017
Property details $0.19…$0.25
Value $0.74…$1.00
Value report $4.20…$5.00
SaaS $54/month/10 reports or PRO $1000/month for unlimited access
12. Example: Zillow improves Zestimate AVM with neural network
- More “human-friendly” way to interpret images and data
- Labeling of all kinds of features (kitchen, materials, sizes etc)
- Adding indoor space data complements property valuations
- Normalization of data - there is no standard how floor plans or images should
be interpreted
- Most importantly: built to reduce valuation error rate and improve home
search accuracy & results
Sources: Inman News, informationweek.com, housely.com. Current error rate 4.5%.
Original text removed in case of copyrights, copypaste below:
Zillow develops ‘neural network’ to identify spaces like humans would
The new technology is expected to increase the accuracy of the Zestimate
Key Takeaways
Zillow announced the development of a "neural network" that allows computers to dissect and identify features in an image the same way humans do.
This network will be used to better identify and tag a home's features, such as granite countertops, a large backyard and wood floors.
This high-tech tagging system is expected to increase the accuracy of Zillow's Zestimates.
Human brains can capture and analyze hundreds of thousands of data points in seconds — which is one of many reasons why a human appraiser often puts online valuations to shame in terms of accuracy.
Zillow is building its own version of human intelligence into its listings and online valuation tool, the Zestimate — dubbed a “neural network,” it will allow machines to identify such niceties as the type of cabinet and countertops used in the kitchen and adjust the home’s value accordingly.
Computer vision technology teaches computers to view, dissect and understand images, and then automatically identify and tag features that would be attractive to a potential buyer, such as granite countertops, high ceilings and french doors.
In March, RealScout founder and CEO Andrew Flachner explained his company’s use of the same technology, saying: “Homebuyers don’t measure ‘home’ in square feet. “Instead, my buyer clients described their home preferences in terms of large backyards, open floor plans and lots of natural light. Flachner noted real estate’s usage of the technology is still in its early days, but argued that with correct use, it can substantially streamline and quicken the online home search process.
“Agents and brokers who effectively integrate these technologies will be able to better cater to their clients’ needs, and will naturally be in higher demand,” he said.
Trulia has already employed computer vision technology; Inman will update this story with more information about how or whether Trulia’s computer vision tools will be different from Zillow’s neural network when it becomes available.
Zillow Group Chief Economist Stan Humphries told The Wall Street Journal the “neural network” will be in use by Q1 2017, and it is expected to lower the current 4.5 percent Zestimate valuation error rate.