Table 3.

Performance of the baseline classifiers.

Model	Performance at different horizons
	Measure	n = 720	n = 1440	n = 2160	n = 2880	n = 3600
KNN	Accuracy	0.740242	0.726611	0.713910	0.700434	0.684015
	Sensitivity	0.495043	0.481722	0.469641	0.456629	0.437423
	Specificity	0.985440	0.971499	0.958178	0.944238	0.930607
	Precision	0.971429	0.944141	0.918231	0.891173	0.863081
	F1_score	0.655859	0.637949	0.621439	0.603851	0.580592
Decision tree	Accuracy	0.738228	0.727695	0.712051	0.695167	0.681382
	Sensitivity	0.491326	0.483891	0.465613	0.445787	0.429058
	Specificity	0.985130	0.971499	0.958488	0.944548	0.933705
	Precision	0.970624	0.944377	0.918143	0.889370	0.866166
	F1_score	0.652406	0.639902	0.617883	0.593892	0.573855
Random forest	Accuracy	0.741481	0.727850	0.713755	0.700434	0.686029
	Sensitivity	0.497831	0.484201	0.469641	0.456629	0.440830
	Specificity	0.985130	0.971499	0.957869	0.944238	0.931227
	Precision	0.970997	0.944411	0.917676	0.891173	0.865046
	F1_score	0.658202	0.640180	0.621311	0.603851	0.584034
Support vector machine	Accuracy	0.741481	0.727850	0.714219	0.700434	0.685564
	Sensitivity	0.497831	0.484201	0.470570	0.456629	0.441140
	Specificity	0.985130	0.971499	0.957869	0.944238	0.929988
	Precision	0.970997	0.944411	0.917825	0.891173	0.863030
	F1_score	0.658202	0.640180	0.622159	0.603851	0.583846
XG boost	Accuracy	0.739312	0.724752	0.711896	0.699814	0.680452
	Sensitivity	0.493185	0.477076	0.464684	0.454771	0.425960
	Specificity	0.985440	0.972429	0.959108	0.944857	0.934944
	Precision	0.971324	0.945365	0.919118	0.891859	0.867508
	F1_score	0.654202	0.634136	0.617284	0.602380	0.571369