https://github.com/rayraegah/recsys

Recommendation system using factorization machine
https://github.com/rayraegah/recsys

factorization-machines python recommender-system

Last synced: 8 months ago
JSON representation

Recommendation system using factorization machine

• Host: GitHub
• URL: https://github.com/rayraegah/recsys
• Owner: Rayraegah
• Created: 2019-05-23T01:50:56.000Z (about 7 years ago)
• Default Branch: master
• Last Pushed: 2019-05-23T01:53:45.000Z (about 7 years ago)
• Last Synced: 2025-04-01T22:32:02.369Z (about 1 year ago)
• Topics: factorization-machines, python, recommender-system
• Language: Python
• Size: 32.2 KB
• Stars: 0
• Watchers: 1
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
FACTORIZATION MACHINE

-------  

Factorization Machine implementation in tensorflow 1.12.0.  

Use the reference training code on-the-fly using the following command:  

```

#--------------------------how to train----------------------------#

./train.sh      \

                

```

 

CODE STRUCTURE

--------------  

 

#--------------------------run script------------------------------#

train.sh  


#----------------------------train---------------------------------#

train.py  

#------------------------common operation--------------------------#

common/  

        model_args.py  

  

#--------convert input text data into tensorflow batch need--------#

data_io/  

       data_parser.py  

#-------------prepare model and build up main framework------------#

models/  

       model.py  

#---------------common algorithm and models for recom--------------#

model_zoo/  

       fm.py  

#-----------------utils for str or data processing-----------------#

utils/  

       utils.py

 


ALGORITHM: FACTORIZATION MACHINE

--------------------------------

![image](images/fm.jpg)

BASELINE

-------  

Our baseline results with 5 features (user_id, user_city, item_id，author_id，item_city):   

  * TRACK2 LIKE TASK: 

  ```  

    auc: 86.5% 

    #------------------------params-------------------------#

    embedding_size = 40

    optimizer = adam  

    lr = 0.0005

  ```

  * TRACK FINISH TASK: 

  ```  

    auc: 69.8% 

    #------------------------params-------------------------#

    embedding_size = 40

    optimizer = adam   

    lr = 0.0001

  ```