The first publicly available “pre-crime” map

A think tank in Rio will soon maintain an online map predicting future crime:

With data from 42 police precincts on crimes committed between January 2010 to March 2016, CrimeRadar tracks some 14 million different crime events. But the app goes beyond mapping historical crimes: Through machine learning and predictive analysis, CrimeRadar will also map out future crime trends—like an open-gov pre-crime heat map…

Muggah says that Igarapé struck a deal with the Institute for Public Security, a state government agency, to build a public-facing mobile app that would show the distribution, intensity, and typologies of crimes across metro Rio. The researchers analyzed data centralized with the ISP along with data from Rio’s 190 system (like 911 in the U.S.) and created 812 categories for crimes. Those break down into capital crimes and violent crimes (like armed assault or intentional homicide), less-intense crimes (thefts, burglaries), and “victimless” crimes (loitering, prostitution).

“We built out a model that uses three data points—the time, the location, and the event—by discriminating in geospatial polygons using these three tiers,” Muggah says. “This algorithm creates a score, a risk score, based on those three data points, for every 250-meter-by-250-meter square unit in the state. You group some of the hundreds of thousands of scores for each sector into deciles to create a simplified, color-coded risk rating, on a scale of 1 to 10.”…

“We have over an 85 percent accuracy of mirroring risk against actual events. The beauty of machine learning is that this improves over time,” Muggah says. “The more data, the more information you feed into it, the higher-resolution your risk projections are going to be.”

Two things strike me as interesting:

  1. The claim that this is for the good of individuals who will be able to then make decisions. What about promoting the public good? This reminds me of apps in the United States that identified tougher neighborhoods but then received backlash.
  2. I’m not sure that 85% accuracy is good or bad. Obviously, such models strive to be much better than that. At the same time, making predictions (and with increasing levels of accuracy regarding times, locations, and actors) in a large city with many variable factors (particularly humans) is difficult. It will be interesting to see how accurate these models can be.

Building a new subway in a big city is difficult, Rio edition

A new subway line in Rio illustrates the issues of constructing subway lines in large cities:

Though it was barely completed in time for the opening ceremonies on August 5, the fact that Line 4 opened this year, let alone this decade, is undeniably because of the Olympics. The state government, which funded the $3.1-billion line, argues that the subway will vastly improve transportation options in the city. The state department of transportation said in an emailed statement that Line 4 will “provide locals and visitors a transportation alternative that’s fast, modern, efficient and sustainable.”

But many outside the government worry that Line 4 was built to primarily serve the Olympics and the upscale real estate developments that are planned in the event’s wake. Critics say Line 4 prioritizes access to the main event venues and wealthy neighborhoods, and disregards the transportation needs of the rest of the city. “This is to serve only the higher classes,” says Lucia Capanema Alvares, an urban planning professor at the Federal Fluminense University. “It’s not to serve the people.”…

This linear design leaves much of the area inside the arc—and the millions of people who live there and in the hinterlands beyond—with little access to rapid transit.

While there are likely unique issues at play in Rio, I suspect these issues would be present in any major city that undertook new subway construction:

  1. Huge costs. Building under a major city is expensive and costs often go beyond budget. The best way to fight this is to have foresight and build such lines sooner rather than later.
  2. Disruption. Again, a large city has all sorts of systems already in place and construction on this scale can take a long time.
  3. Charges of inequality. Who should mass transit serve? Do many major cities primarily have subway and rail service to wealthier areas? (And are these areas better off because they have had mass transit access?) And, why does it take so long to provide service for people who need it?

Such large infrastructure projects are not for the faint of heart but if done well could provide benefits for decades.