The future of (c)old cases

Name: Susan van Esch
Organisation: Q-team (Dutch Police)
Abstract:
  • How does the cold case team of the National Police use data to reinvestigate unsolved murders on useful leads?
  • Which results have been achieved?
  • What are the important success and failure factors?
 

If the Dutch police would decide to solve all the cold cases in their archive today, just reading through the roughly 30 million sheets of paper, would take them about a century...

Lots of cold cases that couldn’t be solved back then, but now, because of things like DNA replication, they can. Often, the DNA profile turns out to be somewhere in a police databank, and the suspect can be re-investigated. There’s one big, glaring problem with this method though – they have no idea where to begin. Cold cases often consist of thousands of undigitized binders of pages.

So Q Police, an innovation team, started experimenting on machine learning. They’re teaching the machine to do forensic DNA screening. The goal is that the AI decides which cases contain promising evidence that could lead to solving the case. Another expectation is that a self-learning system like this one will learn to spot other patterns. There must be connections humans haven’t been able to see with our bare eyes. Detective work is actually just an algorithm; you follow certain steps that will lead to an outcome – balancing between randomness, biases, and real connections. But however good the AI becomes, human detectives will always be in the lead.

Picture of the speaker