Vacasa embraces machine learning in holiday rental pricing in homemade back-end upgrade.

COURTESY: VACASA - (Left to right) Travis Green, Product Lead, Chen Chen, Data Scientist and Nick Mote, Machine Learning Expert.Portland-based vacation rental management firm Vacasa is rejiggering its pricing algorithm.

Calling it Yield Management 2.0, nicknamed Alan (after British boffin Alan Turing) the software was built in house by Vacasa's engineers in its headquarters city, Portland.

The new system will automatically take into account many more variables as landlords try to rent out their vacation homes.

The company's demand-driven pricing engine already sets pricing for more than 5,000 vacation rentals across the country. The new system is designed to bring short-term rental pricing beyond airline and hotel industry standards.

Adopting a popular buzzword, Vacasa's management said Thursday that Yield Management 2.0 will "use machine-learning models."

Machine learning means taking data and applying statistical and algorithmic approaches to find patterns so as to predict outcomes.


The software will mine Vacasa's data from thousands of transactions, it can see what's trending in search, as well as other external data.

It will consider home size, location, luxury classification, local events, and market rates before setting a home's rental price. Vacasa sets prices for the homeowners. Although it does allow them to tweak them if they want, many owners do not want to be that involved.

It will not, however, vary prices depending on who the customer is. All customers will be treated the same.

"Yield Management 2.0 takes this to the next level," said Vacasa co-founder and CEO Eric Breon. "As the lodging space becomes more competitive with the emerging popularity of short-term rentals, Vacasa must continue to innovate and invest in new technology to better serve our homeowners, guests and employees."

COURTESY: VACASA - A Vacasa rental in Montana. New software will allow Vacasa to use many more variables, such as weather and calendar, when pricing vacation homes.

Aspen snowpack

Breon told the Business Tribune, "This will provide value in off peak times, ensuring owners can make money then."

He said the software can now factor in things like school vacations and weather, as well as just the size of the rental home and number of bathrooms.

"We can now look at snow levels in Aspen, and is it Tuesday in a two bedroom on Valentine's Day - subtle patterns."

Users won't see any change in the speed of the Vacasa website. However, Breon says owning the software means they will be able to update and continuously improve it.

The product lead, Travis Green used to work on dynamic pricing at rideshare company Lyft. It was written by a team of 15 in Python, a standard scripting language, which Green calls "fun and powerful."

Founded in 2009, Vacasa manages vacation rental on behalf of homeowners in 16 U.S. states and seven countries.

According to recent Phocuswright data, one in three American travelers stayed in short-term rentals last year compared to one in 10 in 2010.

Vacasa's Chief Analytics Officer Scott Breon developed the company's initial yield management technology in-house. Using that original technology, Vacasa earned its owners an average of 34 percent more than identified competitors in 2016.

Joseph Gallivan

email: This email address is being protected from spambots. You need JavaScript enabled to view it.
Follow us on Twitter
Visit Us on Facebook

Contract Publishing

Go to top
Template by JoomlaShine