Speaker: Peter Brennan The project goal is to identify outbreaks or ‘unusual time events’ associated with time series data pertaining to terrorist events. A detailed investigation of the GTD (Global terrorism database) was undertaken. The aim of the research was to be able to detect early onset of a rise or out breaks in terrorism. Such information would be useful for governments, businesses (such as re-insurers) and risk management professionals. A number of modelling and data visualization techniques were used to gain an understanding of temporal, spatio-temporal and region-temporal terrorist behavior. Key methodologies were identified for analysis of interesting ‘time series count events’ of terrorist related metrics (such as count of incidents or deaths due to terrorism). Interesting time series events would encompass mean shifts or gradual shifts, outbreaks and anomalies. Using a mix of algorithmic techniques from syndromic surveillance methods to time series outlier detection methods, outbreaks of terrorism, mean shifts or gradual shifts in terrorist behaviors are found and correlated with real world events.