Title: Self-driving score filters
Authors: Marcin Zamojski - University of Gothenburg (Sweden) [presenting]
Abstract: A class of approximate score-driven filters is introduced, which is based on automatic differentiation. The agnostic approach requires that a researcher specify a conditional criterion function and that influence functions for the time-varying parameters exist theoretically. We show that in settings where a score model is assumed to be the data-generating process, self-driving filters produce comparable results to analytically derived optimal filters. The small performance loss comes as a trade-off for vastly increased simplicity and implementability. Self-driving filters may be easily implemented in settings where analytical filters are hard or impossible to derive. Therin performance of self-driving filters rivals or improves typical ad-hoc solutions.