TensorFlow London 12: Oliver Gindele 'Recommender systems in Tensorflow'
6 likes7,759 views
The document presents a discussion on recommender systems utilizing TensorFlow, authored by Oliver Gindele, a data scientist from Datatonic. It covers concepts like collaborative filtering, model evaluations, and advanced techniques like deep neural networks, highlighting practical applications and results from a dataset on online dating. The content emphasizes TensorFlow's flexibility in implementing custom algorithms and improving recommender systems through high-level APIs and deep learning methodologies.
![Results - LibimSeTi
MF MLP MF + MLP Research [1]
RMSE 2.137 2.112 2.071 2.077
MAE 1.552 1.541 1.432 1.410
[1] Trust-Based Recommendation: an Empirical Analysis, O’Doherty, Jouili, Van Roy (2008)
Training details:
+ 40 epochs
+ MLP: 4 layers (256 units pyramid)
+ Adam optimiser
+ Results calculated on held out test set (5 rating per user)
+ No tuning of hyperparameters](https://image.slidesharecdn.com/20180214tensorflowlondonolivergindele-recommendersystemsintensorflow1-180215125242/85/TensorFlow-London-12-Oliver-Gindele-Recommender-systems-in-Tensorflow-16-320.jpg)
TensorFlow London 12: Oliver Gindele 'Recommender systems in Tensorflow'
- 1. Recommender Systems with Tensorflow Oliver Gindele @tinyoli oliver.gindele@datatonic.com 14.02.2018
- 2. Who is Oliver? + Data Scientist + PhD in computational physics Who is datatonic? We are a strong team of data scientists, machine learning experts, software engineers and mathematicians. Our mission is to provide tailor-made systems to help your organization get smart actionable insights from large data volumes.
- 5. Collaborative Filtering - Introduction
- 6. Collaborative Filtering - Introduction Objective: + Netflix price (2009) + Solve via SVD (ALS or SGD) + Regression problem
- 7. Finding Love with Numbers
- 8. Online Dating Dataset - LibimSeTi
- 9. Online Dating Dataset - LibimSeTi + http://www.libimseti.cz/ + 2005 + 17,359,346 ratings + 135,359 users + Ratings: 1-10 + Female (%): 69 + Male (%): 31 + Mean(rating): 5.9 + Std(rating): 3.1 userId profileId rating gender
- 10. Tensorflow: High Level APIs Dataset: Estimator:
- 13. MF Model
- 14. Going Deeper - Beyond MF Neural Collaborative Filtering (He et al.)
- 15. Going Deeper - Beyond MF User Metadata Item Metadata userid age gender 1225 ‘30-40’ ‘F’ itemid genre length 44044 ‘Drama’ 129 Add user and item (profile) characteristics
- 16. Results - LibimSeTi MF MLP MF + MLP Research [1] RMSE 2.137 2.112 2.071 2.077 MAE 1.552 1.541 1.432 1.410 [1] Trust-Based Recommendation: an Empirical Analysis, O’Doherty, Jouili, Van Roy (2008) Training details: + 40 epochs + MLP: 4 layers (256 units pyramid) + Adam optimiser + Results calculated on held out test set (5 rating per user) + No tuning of hyperparameters
- 18. Recommender Systems - Improvements + Implicit feedback (Hu, Koren, Volinsky 2008): + Logistic Matrix Factorisation (Johnson, Spotify, 2014): + Negative Sampling + Ranking metrics for better evaluation: HitRate@K, NGCG@K
- 19. Deep Recommender Systems - Advances Wide & Deep model (Cheng et al. 2016) Continuous Features Categorical Features
- 20. Deep Recommender Systems - Advances Deep Neural Networks for YouTube Recommendations (Covington, Adams, Sargi 2006)
- 21. Takeaways + Tensorflow can do more than vision or translation + High level APIs make model building and training painless + Custom algorithms and specific loss functions are easily implemented + Embeddings and hidden layers allow for many ways to improve a recommender system