Researchers from Cornell Tech have developed a method to analyse reporting of incidents to city authorities that can lead to better city services. The analysis looks at delays and volume of reporting of specific incidents neighbourhood by neighbourhood, coupled with anlysis of localised demographic and income levels. The new method has been trialed in both New York City and Chicago to improve delivery of city services across the whole city, and address potential inequalities and gaps in service provision.

The work, which was developed by the Urban Tech Hub at Cornell University, relies on the principle of crowdsourcing, relying on residents reporting incidents and issues to the city authorities. The rate and volume of incident reporting by the public varies neighbourhood by neighbourhood. More affluent and non-minority neighbourhoods are likely to report incidents earlier and more often than poorer neighbourhoods. As a result of this crowdsourcing effect being influenced by income and demographic factors, more affluent neighbourhoods have received more timely services from city authorities than poorer neighbourhoods. The Cornell method aims to correct this disparity in provision of city services between neighbourhoods.

“The 311 system is a big one,” said Nikhil Garg, assistant professor of operations research and information engineering at Cornell Tech, referring to the 311 phone number that residents can call to report incidents and service requests to city authorities. “NYC gets over 3 million service requests a year from the public. For us, this started with a general question: Who is actually participating in all of these participatory mechanisms underlying government?”

The method, which works without knowing exactly when an incident occurred, uses the frequency of reports of the same incident by separate individuals to estimate how long it took for the incident to be first reported. The first report establishes that the incident occurred, and subsequent reports are used to establish the reporting rate.

Applying their method to more than 1 million incident reports in New York City and Chicago, the researchers determined that a neighborhood’s socioeconomic characteristics are correlated with reporting rates.

Garg is senior author of “Quantifying Spatial Under-reporting Disparities in Resident Crowdsourcing,” which was published Dec 5 in Nature Computational Science.

“We’re optimistic that this method can be used to understand underreporting,” he said, “not just in 311 systems, but more broadly where these benchmark problems appear.”

Even after controlling for incident characteristics, such as the level of emergency response needed, they found that some neighborhoods reported incidents three times faster than others. This information could allow city managers to determine the reporting rates of different types of incidents in different neighborhoods, and address problems more equitably.

The disparities corresponded to socioeconomic characteristics of the neighborhoods. In New York City, reporting rates were positively correlated with higher population density; the fraction of people with college degrees; income; and the fraction of the population that is white.

“We find overwhelming evidence that people use 311 systems differently,” said Zhi Liu, lead student author and doctoral student. “And when we’re thinking about the downstream response to those reports, this can serve as a very good reference point. Say no one reports an incident and it’s been sitting there for a prolonged period: We might want to respond to it faster, so that the overall delay is similar across neighborhoods.”

The work was funded in part by the Urban Tech Hub at Cornell Tech.