An AI-assisted CMA tool for pricing homes with confidence for Compass agents
- CompanyCompass
- RoleLead designer
- Date2020
- Websitewww.compass.com
In 2020, I led design at Compass to bring a new Comparative Market Analysis tool (CMA) to their Real Estate platform.
The goal was to help home sellers/buyers determine the number their property might sell for in the market. This is one of the most important and most complex decisions realtors make with their clients. It requires deep knowledge of market trends, the nuances of individual properties, neighborhood characteristics, and access to accurate, meaningful data.
My role
I led the design effort with a cross-functional team of front-end engineers, Ai/ML engineers, product managers, and user researchers from the kickoff to the final launch.
What are CMA documents?
CMAs help realtors communicate and negotiate the likely resale value of properties with their clients. Realtors use them to drive a conversation with their buyer/seller clients and frame the trade-offs and risks when selecting a price. They are treated as a negotiation device and artifact. The documents consist of:
⭐️ Subject
This property is one that clients are looking to buy or sell but are unsure of its market value. This uncertainty is the primary reason for creating the document.
✅ Comparables
These are properties selected by realtors that share similar qualities with the subject property, such as size, location, and amenities, and that sold under similar timeframes and market conditions. In a CMA, they serve as pricing analogies for the subject property.
Problem
It’s difficult selecting accurate comparables. No two properties are the same. Realtors often select comparables where the square footage/layout may be similar to the subject, but it may have a better view, be in a less desirable part of town, or have sold when the market was better. These details can dramatically affect the selling price. To fix this problem, realtors often add pricing adjustments.
Adding adjustments
Realtors apply pricing adjustments to comparables to ensure they are as similar to the subject as possible, providing a more accurate valuation. They are a bit like adding an asterisk beside each item to account for where they diverge.However, doing this is an advanced skill for realtors, and they often don’t feel comfortable doing it formally.
Suggested adjustments
Highlight areas where the ML thinks the comparables differ from the subject property.
Details
Tool tips explain the suggestion and how we calculated it using our model.
AI / ML suggested adjustments
The team and I identified opportunities to leverage Compass’s wealth of listing data, including property details, market trends, and amenities, along with ways to tap into the expertise of the Machine learning and AI engineering team. I collaborated closely with the ML engineering team to identify design opportunities for our agents, such as accelerating the creation of CMAs and generating more meaningful insights for agents to support their pricing strategies better. We developed a ML-powered suggested adjustment feature to assist people in comparing houses in the CMA, identifying their differences with the subject property, and providing suggested price adjustments to account for those differences to make the final number more accurate. The hope was to demystify the process and allow learning, selecting, and tweaking the results.
Agent feedback
Provided a way for agents to leave feedback about the suggestions. The feedback gathered from this menu helped us gauge the quality of the suggestions and helped us improve the model in the future.
Learnings & explorations
We explored ways to keep the adjustment builder as simple as possible. An earlier version displayed one adjustment at a time. It looked good in certain situations but became complicated when the ML suggested 2+ adjustments. In these instances, the interface put too much visual weight on the suggested adjustments, overshadowing the primary input field. The visual and conceptual imbalance triggered a deep negative reaction in the realtors we spoke with. They firmly told us during usability studies that they were the experts, and the design oversold the technology’s abilities to do the work for them. They saw the primary value of technology as something that augments their knowledge and assists them, not replaces them. We took this to heart and used it to guide future iterations and the final build.
The results
We launched the CMA and the adjustment builder experience to the Compass Real Estate platform in 2020. Following the launch, the number of documents created using the CMA platform increased dramatically and was welcomed positively amongst Compass realtors. It played a crucial role during the build-up to our public offering.
▲ 3x increase
in CMAs created at Compass
▲ 2X faster CMA creation time
due to streamlined workflows and suggested adjustments