Academic Research Blog
Real estate developers and investors have a vested interest in discovering new techniques for estimating the direction and magnitude of changes in residential rent within a neighborhood. The Thesis written by Philip Caporaso from MIT hypothesizes and finds evidence that taxi activity can be used as an indicator to predict gentrification and residential rental rates in local neighborhoods.
Why is it important to predict where gentrification will occur? The reason is because a positive shock to residential demand will not impact pricing equally within a city. The variation of residential price growth between neighborhoods in a city is large. Philip studied how future rents can be predicted by using taxi pick-up/drop-off data, as well as median income and location data. In total, this analysis located 764,684,876 drop-offs and 766,648,472 pickups within New York City, a total of 1,531,333,348 data points from 2010-2015.
The results are clear and 99% statistically significant and the effect of a 1% increase in pick-ups/drop-offs results in a 0.1% increase in Rent in the following year. This may seem insignificant, but it provides insight that is forward looking and very valuable to investors and developers looking where to invest next.
Prediction, optimization and analytics is only possible when large amounts of data are made available to researchers and technology firms. When NYC signed Local Law 11 in 2012, they made a leap towards technological advancements.
SquareFeet.ai is a real estate technology firm that uses econometrics and machine learning to set initial prices for new residential developments and optimize them in real time. Together, help us increase efficiency in the design, conception and sales aspects of real estate development.
Book a demo to learn more about how SquareFeet.ai optimizes revenue!