A Hybrid Recommender System for Gaussian Mixture Model and Enhanced Social Matrix Factorization Technology Based on Multiple Interests

Table 4

MAE and P@N results on Epinions and Tencent datasets.

Datasets	Measures	PMF	RTCF	SocialMF	TCARS	CSIT	IMF	ISRec	GMMESMF
Epinions	MAE	0.735	0.672	0.683	0.648	0.668	0.705	0.636	0.591
	P@10	0.365	0.425	0.423	0.438	0.435	0.401	0.441	0.452
	R@10	0.218	0.246	0.244	0.252	0.248	0.223	0.258	0.265
	P@20	0.372	0.437	0.426	0.445	0.439	0.389	0.449	0.478
	R@20	0.223	0.254	0.252	0.257	0.259	0.236	0.263	0.279
Tencent	MAE	0.615	0.592	0.596	0.581	0.587	0.608	0.572	0.553
	P@10	0.388	0.451	0.448	0.472	0.455	0.396	0.476	0.487
	R@10	0.236	0.249	0.246	0.253	0.248	0.238	0.258	0.268
	P@20	0.391	0.470	0.465	0.478	0.472	0.412	0.481	0.496
	R@20	0.241	0.253	0.251	0.259	0.255	0.239	0.262	0.275