Understanding peace through the world news

Voukelatou, Vasiliki; Miliou, Ioanna; Giannotti, Fosca; Pappalardo, Luca

doi:10.1140/epjds/s13688-022-00315-z

EPJ Data Science

Table 3 Performance indicators with respect to GPI ground-truth of nine high performance country models. Overall, 1-month-ahead GPI estimates are significantly more accurate compared to the rest future estimates, especially to the 6-months-ahead time horizon

From: Understanding peace through the world news

Countries	Performance indicators	Prediction framework						Mean
Countries	Performance indicators	1-month-ahead	2-months-ahead	3-months-ahead	4-months-ahead	5-months-ahead	6-months-ahead	Mean
United States	Pearson	0.876	0.838	0.813	0.782	0.750	0.710	0.795
	MAPE (%)	1.197	1.367	1.465	1.592	1.700	1.899	1.537
	RMSE	0.037	0.040	0.042	0.045	0.048	0.053	0.044
United Kingdom	Pearson	0.880	0.849	0.848	0.845	0.853	0.850	0.854
	MAPE (%)	0.632	0.742	0.787	0.821	0.826	0.981	0.798
	RMSE	0.015	0.017	0.017	0.018	0.018	0.020	0.017
Saudi Arabia	Pearson	0.864	0.848	0.849	0.814	0.772	0.781	0.822
	MAPE (%)	3.213	3.406	3.733	4.126	4.396	4.590	3.911
	RMSE	0.089	0.094	0.101	0.111	0.119	0.123	0.106
Portugal	Pearson	0.876	0.868	0.868	0.838	0.835	0.820	0.851
	MAPE (%)	3.691	4.241	4.539	5.221	5.067	5.538	4.716
	RMSE	0.057	0.065	0.067	0.077	0.075	0.080	0.070
Iceland	Pearson	0.840	0.833	0.827	0.810	0.770	0.731	0.802
	MAPE (%)	1.867	2.014	2.114	2.256	2.283	2.367	2.150
	RMSE	0.025	0.027	0.028	0.030	0.030	0.031	0.028
New Zealand	Pearson	0.780	0.748	0.725	0.692	0.689	0.650	0.714
	MAPE (%)	1.444	1.538	1.633	1.651	1.741	1.793	1.633
	RMSE	0.023	0.024	0.025	0.026	0.026	0.027	0.025
DR Congo	Pearson	0.820	0.815	0.790	0.762	0.740	0.728	0.776
	MAPE (%)	2.409	2.792	2.856	2.899	2.957	3.120	2.839
	RMSE	0.088	0.099	0.103	0.105	0.107	0.113	0.103
Pakistan	Pearson	0.848	0.772	0.720	0.668	0.672	0.640	0.720
	MAPE (%)	0.749	0.858	0.922	1.006	1.052	1.036	0.937
	RMSE	0.029	0.033	0.036	0.040	0.040	0.040	0.036
Yemen	Pearson	0.832	0.771	0.746	0.722	0.687	0.662	0.737
	MAPE (%)	5.063	6.033	6.810	7.287	7.801	7.999	6.832
	RMSE	0.207	0.243	0.267	0.283	0.300	0.309	0.268
Yemen^∗	Pearson	0.953	0.945	0.934	0.922	0.908	0.898	0.892
	MAPE (%)	2.645	2.990	3.440	3.652	3.914	4.171	4.287
	RMSE	0.116	0.129	0.144	0.154	0.166	0.176	0.180

^∗For the training of this model, the most recent 36 monthly values are used, as compared with the rest of the countries’ models that are trained with the most recent 72 monthly values.

Back to article page