Updating Prediction Models for Predictive Process Monitoring

Predictive monitoring is a key activity in some Process-Aware Information Systems (PAIS) such as information systems for operational management support. Unforeseen circumstances like COVID can introduce changes in human behaviour, processes, or computing resources, which lead the owner of the process or information system to consider whether the quality of the predictions made by the system (e.g., mean time to solution) is still good enough, and if not, which amount of data and how often the system should be trained to maintain the quality of the predictions. To answer these questions, we propose, compare, and evaluate different strategies for selecting the amount of information required to update the predictive model in a context of offline learning. We performed an empirical evaluation using three real-world datasets that span between 2 and 13 years to validate the different strategies which show a significant enhancement in the prediction accuracy with respect to a non-update strategy. © 2022, Springer Nature Switzerland AG.

Criminality in context COVID year 2020 and approach of a proposal in neurocriminology

The criminality behavior during the year 2020 evidenced variations associated with changes in population dynamics throughout the country. This article, using descriptive elements, exposes the characteristics of crime in Colombia during the year 2020 and the criminogenic context associated with the transformations of crime, with emphasis on homicide. In particular, the article includes a section that reflects on the contributions of neurocriminology to the understanding of criminal behavior. Among the conclusions are: 1) a significant reduction in homicide, which represented the lowest rate of the last 46 years in Colombia, equivalent to 23.8 homicides per one hundred thousand inhabitants. 2) a decrease equivalent to 29% of impact crimes occurred in the country when comparing 2019 with 2020. 3) associated with a year of health emergency the National Police captured 173,217 subjects for the commission of different crimes and according to analytical exercises carried out in territories, police units increased their workload with new tasks derived from COVID-19 attention and prevention measures.