Dr Mihai Croicu successfully defends thesis

On 21 March, Dr Mihai Croicu successfully defended his PhD dissertation, "Forecasting Battles: New Machine Learning Methods for Predicting Armed Conflict."

As per tradition at the DPCR, a large part of the research community was there to support him.

Mihai’s work, developed within the Violence & Impacts Early-Warning System (VIEWS), represents a major step forward in ML/AI-powered conflict forecasting. According to Mihai’s opponent Thomas Chadefaux, the thesis:

• Improves forecasting accuracy by integrating real-time event data.
  
  
• Develops new methods for handling geospatial uncertainty in conflict datasets.
  
  
• Introduces active learning to extract predictive features from text data.
  
  
• Shifts focus from locations to actors. Improves escalation predictions.
  
  
• Explores media biases in conflict event reporting.
  
  Mihai’s dissertation summary (kappa) provides a compelling 60-page overview of his impressive contributions to the field.
  
  The department extends its gratitude to Thomas Chadefaux from Trinity College Dublin for serving as Mihai’s opponent, as well as Karina Shyrokykh, Sara Stymne and Magnus Oberg, who served on the grading committee.
  
  Last but not least, the DPCR thanks Mihai´s supervisors Håvard Hegre, Joakim Kreutz, and Nils B. Weidmann for their invaluable guidance throughout his PhD journey.