01697824

Component

Urban transportation and land use models have used theory and statistical modeling methods to develop model systems that are useful in planning applications. Machine learning methods have been considered too ’black box’, lacking interpretability, and their use has been limited within the land use and transportation modeling literature. The authors present a use case in which predictive accuracy is of primary importance, and compare the use of random forest regression to multiple regression using ordinary least squares, to predict rents per square foot in the San Francisco Bay Area using a large volume of rental listings scraped from the Craigslist website. The authors find that they are able to obtain useful predictions from both models using almost exclusively local accessibility variables, though the predictive accuracy of the random forest model is substantially higher.

This paper was sponsored by TRB committee ADD30 Standing Committee on Transportation and Land Development.

19-05881

English

15p

2019

Transportation Research Board 98th Annual Meeting

Digital/other

Figures; References; Tables

Accessibility; Accuracy; Algorithms; Alternatives analysis; Data analysis; Least squares method; Machine learning; Mathematical prediction; Regression analysis; Rent

San Francisco Bay

Data and Information Technology; Economics; Planning and Forecasting; Transportation (General)

Transportation Research Board Annual Meeting 2019 Paper #19-05881

TRIS, TRB, ATRI

Dec 7 2018 9:38AM