Download as PDF, PPTX
Uploaded byTrieu Nguyen
Introduction to Recommendation Systems
The document provides an introduction to recommendation systems, detailing how AI and data science help suggest content to users. It outlines key types of recommendation systems including collaborative filtering, content-based filtering, and hybrid systems, alongside their benefits for businesses. Additionally, it discusses the technical aspects of building a data pipeline for video recommendations and emphasizes the importance of understanding user preferences to enhance user experience.
More Related Content
Similar to Introduction to Recommendation Systems
![[Final]collaborative filtering and recommender systems](https://cdn.slidesharecdn.com/ss_thumbnails/finalcollaborativefilteringandrecommendersystems-141103044224-conversion-gate01-thumbnail.jpg?width=640&height=640&fit=bounds)
![[Notes] Customer 360 Analytics with LEO CDP](https://cdn.slidesharecdn.com/ss_thumbnails/notescustomer360analyticswithleocdp-220126053232-thumbnail.jpg?width=640&height=640&fit=bounds)
Introduction to Recommendation Systems
- 1. Introduction to Recommendation Systems forNews, Education and Entertainment By Trieu Nguyen - Lead Engineer at FPT Telecom My email: [email protected]
- 2. How computers know whatwe really want ? By using AI, Big Data or Data Science !?
- 3. People don’t knowwhat they want until you recommend it to them.
- 4. 3 key ideas aboutdata 1. Data Product 2. Data Engineering 3. Data Science 1. Recommendation Systems in Practice 2. Types of Recommendation Systems 3. Building Data Pipeline for Video Recommendation System 3 key ideas about the slide
- 5. After this talk,I hope everyone can understand above big picture
- 6. 1 - TheWorld of Recommendation Systems
- 7.
- 8. LinkedIn: "Jobs youmay be interested in"
- 9. Your Recommendations fromMOOC Coursera
- 10. “Recommended for you”by YouTube User-based Collaboration Filter Item-based Collaboration Filter
- 11.
- 13. That my books,mostly from Amazon :)
- 14.
- 16. WHY SHOULD WEUSE RECOMMENDATION ENGINES? 1. Two-thirds of movies watched by Netflix customers are recommended movies 2. 38% of click-through rates on Google News are recommended links 3. 35% of sales at Amazon arise from recommended products Steve Jobs: “A lot of times, people don’t know what they want until you show it to them.”
- 17. Beneficial features ofthe product recommendation engine to marketers 1. Retain user loyalty 2. Builds the volume of user traffic 3. Delivers more convenient UX to your user 4. Give your business a wider marketplace
- 18. So what isrecommendation engine ? In technical terms, a recommendation engine problem is to develop a mathematical model or objective function which can predict how much a user will like an item. If U = {users}, I = {items} then F = Objective function and measures the usefulness of item I to user U, given by: F: U x I → R Where R = {recommended items}. For each user u, we want to choose the item i that maximizes the objective function:
- 19. 2 - WHATARE THE DIFFERENT TYPES OF RECOMMENDATION ENGINES?
- 20. 3 important typesof recommender systems 1. Collaborative Filtering 2. Content-Based Filtering 3. Hybrid Recommendation Systems
- 21. User-based Collaborative Filtering Collaborativefiltering methods are based on collecting and analyzing a large amount of information on users’ behaviors, activities or preferences and predicting what users will like based on their similarity to other users. A key advantage of the collaborative filtering approach is that it does not rely on machine analyzable content and therefore it is capable of accurately recommending complex items such as movies without requiring an “understanding” of the item itself
- 22.
- 23. Content Based Filtering (Item-based collaborative filtering) Content-based filtering methods are based on a description of the item and a profile of the user’s preference. In a content-based recommendation system, keywords are used to describe the items; beside, a user profile is built to indicate the type of item this user likes.
- 24. Content Based Filtering (Item-based collaborative filtering)
- 25. Hybrid Recommendation Systems Thesemethods can also be used to overcome some of the common problems in recommendation systems such as cold start and the sparsity problem.
- 26.
- 27. Example of HybridRecommendation Systems User-based Collaboration Filter Item-based Collaboration Filter
- 28.
- 29. 3 - BuildingData Pipeline for Video Recommendation System
- 31. Simple version ofVideo Data Pipeline https://github.com/rfxlab/rfx-video-analytics
- 32. Simple Recommendation Enginewith Apache Spark MLLib
- 33. My personal answeris “building 2 things” 1. Data Ecosystem 2. Choice Architecture How computers know what we really want ?
- 34. Data Ecosystem with{ Product + Engineering + Science }
- 35. Choice Architecture forrecommendation systems
- 36.
- 37.
- 38. Follow this pageto get more information http://BigDataVietnam.org https://fb.com/bigdatavn
- 39. Ref links aboutApache Spark http://blogs.quovantis.com/recommendation-engine-using-apache-spark/ https://chimpler.wordpress.com/2014/07/22/building-a-food-recommendation -engine-with-spark-mllib-and-play http://ampcamp.berkeley.edu/big-data-mini-course/movie-recommendation-wi th-mllib.html https://stanford.edu/~rezab/classes/cme323/S16/ https://www.codementor.io/jadianes/building-a-recommender-with-apache-sp ark-python-example-app-part1-du1083qbw https://bugra.github.io/work/notes/2014-04-19/alternating-least-squares-meth od-for-collaborative-filtering/
- 40.