search

yingtaoluo / Spatial-Temporal-Attention-Network-for-POI-Recommendation

Codes for a WWW'21 Paper. POI recommender system for location/trajectory prediction.
https://doi.org/10.1145/3442381.3449998
170 stars 38 forks source link

Using model #33

Closed pial98 closed 3 months ago

pial98 commented 4 months ago

As this model is for generating future POIs , can it be used for showing next POIs if changes are made to inference method?

yingtaoluo commented 3 months ago

I am not sure that I understand your question. Do you mind elaborating it again?

pial98 commented 3 months ago

Hello, Firstly I want to know how this model generating test accuracy and validation accuracy as there are no information about that. Secondly , I want to know that if this model can be modified so that I can know where a user will go in the next visit by analyzing that user's past visits.

On Wed, Jul 24, 2024, 1:21 PM yingtaol @.***> wrote:

I am not sure that I understand your question. Do you mind elaborating it again?

— Reply to this email directly, view it on GitHub https://github.com/yingtaoluo/Spatial-Temporal-Attention-Network-for-POI-Recommendation/issues/33#issuecomment-2247087765, or unsubscribe https://github.com/notifications/unsubscribe-auth/BCDZCMYYHYOG72YWQ67BOBDZN5IWLAVCNFSM6AAAAABK5BWGROVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDENBXGA4DONZWGU . You are receiving this because you authored the thread.Message ID: <yingtaoluo/Spatial-Temporal-Attention-Network-for-POI-Recommendation/issues/33/2247087765 @github.com>

yingtaoluo commented 3 months ago

The code has surely covered the test and validation eval. See lines 144 and 147 in train.py.

STAN is already predicting the next visit by analyzing user's past visits. I am still confused. Are you suggesting you want to directly know the next visit at any potential geographical coordinates? That might be possible, but will be hard.

yingtaoluo commented 3 months ago

If there are other concerns, feel free to reopen the issue.

pial98 commented 2 months ago

Hello,

If I want to use your model in a tourism based website then how can I do it? As after running your code I only get to know about the training and validation accuracy.I am constantly trying to change the inference method of the train.py but nothing is working as I am expecting.

On Sat, Aug 17, 2024, 12:16 PM yingtaol @.***> wrote:

If there are other concerns, feel free to reopen the issue.

— Reply to this email directly, view it on GitHub https://github.com/yingtaoluo/Spatial-Temporal-Attention-Network-for-POI-Recommendation/issues/33#issuecomment-2294676178, or unsubscribe https://github.com/notifications/unsubscribe-auth/BCDZCMY3NQL2P2ISFQJUIBLZR3TDPAVCNFSM6AAAAABK5BWGROVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDEOJUGY3TMMJXHA . You are receiving this because you authored the thread.Message ID: <yingtaoluo/Spatial-Temporal-Attention-Network-for-POI-Recommendation/issues/33/2294676178 @github.com>