recommendation_hands

1. Docker
Recommendation hands on
2020-12-16
Orozco Hsu

2. Agenda
• Use case
• Google search, Amazon online shopping
• What is recommendation system
• Hands-on practices
• Baseline
• Content-based/ CF
• Lightfm
• NCF

3. Prepare training environment
• Start container
• RUN =>
• RUN => docker run --rm -e JUPYTER_ENABLE_LAB=yes -v "/tmp/work":/home/jovyan/work -p
20000:8888 jupyter/datascience-notebook
cd /tmp; mkdir docker_20201209

4. Prepare training environment
• Place docker_20201216 folder in /tmp/work folder
• Code: https://github.com/orozcohsu/ntunhs_2020/tree/master/docker_20201216

5. Prepare training environment
• Browser jupyter-notebook

6. Use case

7. Use case

8. Use case
Recsys

9. What is recommendation system
• Which one is better for bringing more jam sales?
• https://medium.com/@przemekszustak/less-is-more-the-paradox-of-choice-
behavioural-economics-in-ux-318849b2d70

10. What is recommendation system
• Recommendation types
• Demographic-based Recommendation
• Content-based Recommendation
• Collaborative Filtering Recommendation
• User-based CF
• Item-based CF
• Model based Recommendation
• Machine learning algorithms (lightfm, ALS, SVD…)
• Deep learning

11. What is recommendation system
• Demographic-based Recommendation

12. What is recommendation system
• Content-based Recommendation

13. What is recommendation system
• Collaborative Filtering Recommendation
• User-based
• Item-based

14. What is recommendation system
Ref. https://towardsdatascience.com/introduction-to-recommender-systems-6c66cf15ada

15. What is recommendation system
• If sparsity is greater than 50%, you can’t use CF

16. What is recommendation system
• Normalization the Ratings

17. What is recommendation system
• Model based Recommendation (matrix decomposition)

18. What is recommendation system

19. What is recommendation system
• Model optimization
• Precision@K: Find the top K recommended items and check result of user
actual reaction ratio
• Use Precision@K to optimize mode performance
• Model evaluation
• A/B test => on line evaluation
• RMSE, Precision, Recall, F1 => offline evaluation

20. Hands-on practices
• Raw data (with visitor’s page-view)

21. Hands-on practices
• Set training and validating set
Training
[appearance>1]
Validating
[appearance=1]
Hold-one-out evaluation for baseline evaluation
Appearance=1 means the latest view of each visitor

22. Hands-on practices
• MRR (Mean reciprocal rank)
https://en.wikipedia.org/wiki/Mean_reciprocal_rank
The first selected item has a higher score, that means BETTER!
Baseline MRR = 0.02096631601316712
Not so good

23. Hands-on practices [baseline]
• Demo code
• RUN =>
• You RUN =>
01_baseline_small.ipynb
01_baseline.ipynb

24. Hands-on practices [ubcf, ibcf]
• Raw data (with user’s ratings)
users
Pearson
Correlation

25. Hands-on practices [ubcf, ibcf]
• Demo code
• RUN =>
• YOU RUN =>
02_Collaborative_Filtering_small.ipynb
02_Collaborative_Filtering.ipynb

26. Hands-on practices [ubcf, ibcf]
• ubcf
Recommendation Results
Sources
User1
User4
….
item1 item5item2 item3 item4
user_similarity_matrix
user2movie

27. Hands-on practices [ubcf, ibcf]
• ibcf
User1
User4
….
item1 item5item2 item3 item4
item_similarity_matrix
user2movie
Sources

28. Hands-on practices [cb]
• Demo code
• RUN => 03_Content_Based_Filtering.ipynb
TFIDF is a measure of originality of a word by comparing the
number of times a word appears in a doc with the number of docs
the word appears in
Extracting keywords from text with TFIDF
Matrix dot vector used to computing similarity

29. Hands-on practices [cb]
• Find most similar item with Harry Potter

30. Hands-on practices [Lightfm]
• It make to incorporate both item and user metadata into the
traditional matrix factorization algorithms
• It represents each user and item as the sum of the latent
representations of their features, thus allowing recommendations to
generalize to new items (via item features) and to new users (via user
features)

31. Hands-on practices [Lightfm]
• Divide user/ movie feature matrix with F features

32. Hands-on practices [Lightfm]
• Demo code
• RUN =>
• YOU RUN=>
04_LightFM_small.ipynb
no_components: the dimensionality of the feature latent embeddings
learning_schedule: 'adagrad', 'adadelta'
loss: 'logistic', 'bpr', 'warp', 'warp-kos'
learning_rate: nitial learning rate for the adagrad learning schedule
Ref. https://making.lyst.com/lightfm/docs/_modules/lightfm/lightfm.html
04_LightFM.ipynb

33. Hands-on practices [NCF]
• Confusion matrix
• Acc = (TP+TN)/(TP+FP+FN+TN)
• Recall = (TP)/(TP+FN)
• Precision = (TP)/(TP+FP)
Fact (H1 = True) Fact (H1 = False)
Prediction (True) TP FP
Prediction (False) FN TN
Add some fake backgroup (negative examples) if your precision is lower
Example: add FP(false-positive) examples from testing as negative examples to train a new model

34. Hands-on practices [NCF]
• Demo code
• YOU RUN => 05_NCF.ipynb
NCF MRR = 0.24179100068337941
The difference between implicit and explicit feedbacks is what we only see the items that each user
may be interested in.
In order to training Deep-Learning model, we need to create some negative training examples. The
faster way is to randomly generating some negative examples.

35. Hands-on practices [NCF]
• MLP (multilayer perceptron)
• Copy and paste get_mlp_model function code from 05_NCF.ipynb to Net2Vis
webpage
• https://viscom.net2vis.uni-
ulm.de/FAPokAxSXSrKPD9xCYjbDerXwa3WAZzeoL5ST6b1pOkCdPHZDo

36. Reference
• Credit to https://github.com/khuangaf/tibame_recommender_system
• We didn’t cover so much about Deep-Learning topics
• MLP
• CNN
• Dense
• Flatten
• Activation
• Add
• Dropout
• …