This week N/LAB attended ICDM in Barcelona, presenting work by Dr. James Goulding (N/LAB), Dr. Simon Preston (School of Mathematical Sciences, University of Nottingham) and Dr. Gavin Smith (N/LAB). The paper, titled Event Series Prediction via Non-homogeneous Poisson Process Modelling, considers prediction of data streams where events occur at random arrival times rather than at the regular, tick-tock intervals of traditional time series, an increasingly prevalent type of data in practice.
The full citation is:
Goulding, J, Preston, S. P., and Smith, G., 2016. Event Series Prediction via Non-homogeneous Poisson Process Modelling In: IEEE International Conference on Data Mining (ICDM).