We are excited to invite you to our bi-monthly Meetup. This session will focus on using machine learning results as forensic evidence in criminal cases with a Bayesian approach. Our guest speaker is Sander Dalm, a Data Scientist at the Netherlands Forensic Institute. Schedule:
• Doors open at 18:00; food will be provided
• Talk starts at 19:00
• Drinks as of 20:00
Large quantities of digital information are an increasingly common source of forensic evidence. To find patterns in these data, the Netherlands Forensic Institute (NFI) employs machine learning to evaluate hypotheses in criminal cases.. But how does one take the output of a machine learning algorithm and turn it into sound statistical evidence to be accepted by a judge? Can such algorithms directly determine the probability of a suspect being guilty? The answers to these questions are explained with the help of a case study. In the case study we will discuss how to determine, based on cell phone location data, whether two cell phones belong to the same person or to different persons. There will also be an in-depth discussion about how to deal with uncertainty in your measurements and how to quantify your findings in a way so that the result can be used in court. Sander Dalm attained a Msc. degree in Biological and Cognitive Psychology from the Erasmus University Rotterdam in 2009. He has worked as a statistical researcher for Statistics Netherlands and the Ministry of Education, Culture and Science. He is currently employed by the Netherlands Forensic Institute as a data scientist, where his job is to find patterns in large quantities of data in criminal cases using machine learning.
Claim the event and start manage its content.I am the organizer