Research Article

UPTDNet: A User Preference Transfer and Drift Network for Cross-City Next POI Recommendation

Table 3

Comparison of different methods for the next POI recommendation on the Dallas-Austin dataset.

MethodDallas⟶AustinAustin⟶Dallas
MRRRec@1Rec@5Rec@10MRRRec@1Rec@5Rec@10

PRME0.08430.04040.11390.17280.17820.11460.23510.2936
RNN0.09970.05130.13480.18640.16430.09760.22860.2941
Time-LSTM0.09850.05030.13370.18390.11650.04880.17130.2538
Caser0.09990.04670.13740.19170.17330.09010.24210.3450
AttRec0.10570.04170.15760.22850.20910.12160.29820.3918
DeepMove0.12380.06920.16710.22180.21000.12890.28260.3607
LSTPM0.13130.07420.18010.23730.23070.15010.29610.3871
GETNext0.12550.07000.17500.23380.22090.14440.25560.3639
PLSPL0.14550.08280.20260.27090.23410.14270.32510.4129
Flashback0.13520.06590.19740.26720.19380.11190.25950.3524
Flashback-R0.15760.08280.22480.29970.22740.14520.29290.4012
UPTDNet0.17840.10070.24870.33480.27720.18930.36910.4607

The bold values indicate the best model results. Italic values indicate the second best model results.