Carnegie Mellon Project Uses Machine Learning To Help Apartment Hunters Estimate Utility Costs Algorithm Considers User’s Lifestyle To Identify Perfect Rental

Byron SpiceFriday, May 15, 2015

EDigs will help people find the perfect rental property by using a machine learning algorithm that can estimate utility costs based on both the housing unit and the renter’s lifestyle.

A new online resource from Carnegie Mellon University seeks to help people find the perfect rental property by using tools such as a machine learning algorithm that can estimate utility costs based not only on the housing unit itself but on the renter’s lifestyle.

The free service, EDigs, is available through either a website or an Android app, and is part of a research project on livability and sustainability directed by Jennifer Mankoff, an associate professor in the Human-Computer Interaction Institute, and Associate Professor of Design Cameron Tonkinwise.

Mankoff said EDigs will incorporate a number of features useful to prospective tenants, including a review system that employs photos the user can annotate. It will focus on features that are compatible with and useful to mobile users.

The most distinctive of its initial features is the tool for estimating utility costs. This employs a type of artificial intelligence known as machine learning to provide personalized estimates for each user. The algorithm draws on data from the Residential Energy Consumption Survey conducted by the U.S. Energy Information Administration and on user-supplied information about personal behaviors and lifestyle.

The project is sponsored by Carnegie Mellon’s Metro 21, a multidisciplinary initiative to develop and evaluate solutions to challenges affecting the economy and quality of life in metropolitan areas.

For more information, visit the EDigs website.

For More Information

Byron Spice | 412-268-9068 | bspice@cs.cmu.edu