Identifying and predicting social lifestyles in people’s trajectories by neural networks

EPJ Data Science

Table 6 Performance measures averaged over all trajectories of all users in a CV5 experiment. For all measures, except the Hamming loss, higher is better. CK is for Cohen’s Kappa score; JS is for Jaccard similarity

	Accuracy	f1 score	Precision	Recall	CK score	JS score	Hamming loss
HMM	0.14	0.13	0.14	0.16	0.07	0.14	0.86
NB	0.18	0.09	0.17	0.12	0.07	0.18	0.82
LSVM	0.25	0.21	0.23	0.21	0.18	0.25	0.75
RSVM	0.15	0.05	0.06	0.09	0.04	0.15	0.85
PSVM	0.12	0.02	0.01	0.07	0.00	0.12	0.88
SVC	0.25	0.22	0.23	0.22	0.18	0.25	0.75
CNN	0.34	0.30	0.32	0.30	0.27	0.34	0.66
RNN	0.35	0.31	0.32	0.31	0.28	0.35	0.65
LSTM	0.48	0.45	0.46	0.44	0.43	0.48	0.52
BLSTM	0.49	0.46	0.47	0.45	0.44	0.49	0.51
CLSTM	0.52	0.48	0.50	0.48	0.47	0.52	0.48
CBLSTM	0.51	0.48	0.50	0.47	0.46	0.51	0.49