A first in the United States: ComfortPredict IS LIVE IN BROOKLYN

Downtown Brooklyn has become an outdoor laboratory for a few days. Qucit is taking advantage of this unique opportunity to employ its ComfortPredict technology to survey the pedestrians and find out what they think about the public spaces in the neighborhood.

 

The Downtown Brooklyn Partnership  (DBP) is a not-for-profit local development corporation that serves as the primary champion for Downtown Brooklyn. One of DBP’s initiatives is the recently launched Living Lab program, with which DBP is partnering with tech startups like Qucit to solve operational and quality of life challenges facing cities.  The program encourages participants to use DBP-operated public spaces as testing grounds for smart city technologies and share their findings with DBP thus enabling more efficient management and strategic programming of the public realm. The organization is working closely with incubators, accelerators, and entrepreneurial hubs to identify startups that can improve the neighborhood.

 

Qucit had the chance to interview people at random in public spaces throughout Downtown Brooklyn and assess their opinions about the neighborhood. The findings are then associated with a set of data on public spaces using Machine Learning models. With this method, one can objectively qualify the perception of a district according to its residents and visiting pedestrians.  This is the ComfortPredict model.

 

What is ComfortPredict? How does it work?

 

ComfortPredict is a product intended for use by multiple actors including (local authorities, transit stations & airports, cleaning operators, property developers and managers). It makes it possible to locate and predict the different perceptions of the users of a space according to various factors. It also quantifies the external factors impacting the perception of individuals in order to improve their viewpoints by anticipating factors of discomfort.

We create heat maps to illustrate the perceptions of comfort from users of spaces in different locations. Using Qucit software, a city or neighborhood can visualize the data and filter specific spatial aspects of interest. This projection makes it possible to establish a diagnosis on the spaces analyzed: which places are less frequented or, less appreciated, and why?

 

 

Over the course of one week, more than 800 surveys were conducted in Downtown Brooklyn. The survey consisted of about twenty questions dealing with the feelings of perception, satisfaction and the profile of the respondents using a proprietary Qucit protocol that collects a wide range of information in a short period of time.

 

Lucie and Marie were our special envoys there!

These surveys in Downtown Brooklyn were the first carried out in the United States. This area, located southeast of Manhattan, is well-known as an important central business district (CBD) in New York City. The third largest CBD after Midtown Manhattan and Lower Manhattan, the district is a veritable hive where tens of thousands of people swarm during the day. Approximately 307,000 people reside in the area. Downtown Brooklyn is recognized as a world-class business, cultural, educational, residential, and retail destination.

 

This is the area within Downtown Brooklyn that is being studied

Most of the survey respondents lived, worked or studied in Downtown Brooklyn, where we conducted this campaign. We noted a clear difference between weekdays and weekends in terms of audience profile.

 

Smart city technologies make cities safer, cleaner and more enjoyable. The ‘Living Lab’ program implemented by Downtown Brooklyn Partnership aims to improve quality of life for local residents and visitors, and the environment for local businesses, while allowing smart cities entrepreneurs and technologists to take advantage of the district’s rich data and public spaces in order to achieve greater impact. If the model is applicable in one neighborhood in Brooklyn, it is potentially applicable in other neighborhoods, and in cities around the world.

Share This