Wakoopa Recommendations Engine on AWS

Loading...

Flash Player 9 (or above) is needed to view presentations.
We have detected that you do not have it on your computer. To install it, go here.

2 comments

Comments 1 - 2 of 2 previous next Post a comment

Post a comment
Embed Video
Edit your comment Cancel

8 Favorites & 1 Group

Wakoopa Recommendations Engine on AWS - Presentation Transcript

  1. Menno van der Sman Lead Developer Coen Stevens Recommendation Engineer
  2. Mission: Discover software & games
  3. Updates
  4. Searching powered by
  5. Recommendations Codename: Ludwig
  6. How to get started? Research Mathemagicians Amazon, Netflix etc Peter Tegelaar & Coen Stevens Ludwig created recommender system in ruby running on EC2
  7. Challenges when building your first recommender system
  8. Data what do we have? Usage (implicit) vs. Ratings (explicit) • Noisy • Accurate • Only positive • Positive and negative feedback feedback • Easy to collect • Hard to collect
  9. Item-Based Collaborative Filtering User software usage matrix Software items 220 90 180 22 280 12 42 80 Users 175 210 210 45 165 14 35 195 13 25 100 50 185 35 190 60 65 185
  10. Classified user software usage matrix (1, 2, 3) Software items 3 2 2 2 3 2 1 2 Users 3 3 2 3 2 1 2 2 3 2 3 2 2 2 3 1 2 3
  11. How do we predict the probability that I would like to use GMail? Software items 3 2 2 2 3 2 1 2 Users 3 3 ? 2 3 2 1 2 2 3 2 3 2 2 2 3 1 2 3
  12. Calculate the similarities between Gmail and the other software items. Software items 3 2 2 2 3 2 1 2 Users 3 3 2 3 2 1 2 2 3 2 3 2 2 2 3 1 2 3 Similarity(Firefox, Gmail)
  13. Calculate the similarities between Gmail and the other software items. Gmail similarities 0.6 3 2 2 2 0.8 3 2 1 2 1.0 3 3 2 3 0.4 2 1 2 2 3 2 0.4 3 2 2 2 3 0.3 1 2 3 0.3
  14. Calculate the predicted value for Gmail Gmail similarities User usage 0.6 3 0.8 3 1.0 0.4 2 0.4 0.3 3 0.3
  15. Calculate the predicted value for Gmail Gmail similarities User usage We take only the ‘K’ most similar items (say 2) 0.6 3 0.8 3 1.0 0.4 2 0.4 0.3 3 0.6*3 + 0.8*3 = 2.8 0.6 + 0.8 + 0.4 + 0.3 0.3
  16. Calculate all unknown values and show the Top-N recommendations to each user Software items 3 2 ? 2 ? ? 2 3 2 1 ? 2 ? ? Users 3 3 ? 2 ? 3 ? 2 1 2 2 3 2 ? ? 3 2 2 ? 2 3 ? 1 ? 2 ? ? 3
  17. Metrics measure for success Space complexity: O(m + Kn) Computational complexity: O(m + n²) Performance: Root Mean Squared Error
  18. Evaluating the approach Maximize ( performance cost ) This is easy with EC2
  19. Why EC2? Low cost Flexibility Ease of use
  20. Infrastructure Wakoopa EC2 checkout Repository Computing Application power Database ssh tunnel Big Database
  21. Want more? http://recked.org Time & place TBD

+ tracylaxdaltracylaxdal, 2 years ago

custom

1746 views, 8 favs, 3 embeds more stats

Menno van der Sman, Lead Engineer of Wakoopa presen more

More info about this document

© All Rights Reserved

Go to text version

  • Total Views 1746
    • 1720 on SlideShare
    • 26 from embeds
  • Comments 2
  • Favorites 8
  • Downloads 53
Most viewed embeds
  • 20 views on http://deploy.visualcv.com
  • 5 views on http://www.tallerdeinformatica.com.ar
  • 1 views on http://tallerdeinformatica.com.ar

more

All embeds
  • 20 views on http://deploy.visualcv.com
  • 5 views on http://www.tallerdeinformatica.com.ar
  • 1 views on http://tallerdeinformatica.com.ar

less

Flagged as inappropriate Flag as inappropriate
Flag as inappropriate

Select your reason for flagging this presentation as inappropriate. If needed, use the feedback form to let us know more details.

Cancel
File a copyright complaint
Having problems? Go to our helpdesk?

Categories

Groups / Events