Title :
Predicting onsets of genocide with sparse additive models
Author :
Semenovich, D. ; Sowmya, Arcot ; Goldsmith, B.E.
Author_Institution :
Sch. of Comput. Sci. & Eng., Univ. of New South Wales, Sydney, NSW, Australia
Abstract :
Prevention of genocide is one of the most important challenges before the international community. In this paper we apply recent machine learning techniques to forecast the onset of political instability and genocide. Specifically, we employ sparse additive models which are both flexible and maintain interpretability of the results. Our model demonstrates a reasonable degree of forecasting performance over the hold-out period 1988-2003.
Keywords :
ethical aspects; forecasting theory; learning (artificial intelligence); politics; flexible interpretability; genocide; hold-out period; international community; interpretability maintenance; machine learning techniques; onset political instability forecasting; onsets prediction; sparse additive models; Additives; Casting; Educational institutions; Forecasting; Logistics; Predictive models; Standards;
Conference_Titel :
Pattern Recognition (ICPR), 2012 21st International Conference on
Conference_Location :
Tsukuba
Print_ISBN :
978-1-4673-2216-4
