Recommender Systems (Conceptual)

Presented at Z1 Data

Transcript

1. Recommender Systems (Conceptual) Samnang Chhun | @samnangchhun
2. Recommender Systems
3. Three Common Approaches to Recommender Systems
4. Content-based Filtering
5. Content-based Filtering
6. Collaborative Filtering
7. Collaborative Filtering
8. References • MLlib | Apache Spark (OSS) • Disco: Recommendations for Ruby and Rails using collaborative filtering (OSS) • Gorse: is an open source recommendation system written in Go (OSS) • Recombee: Artificial Intelligence Powered Recommender as a Service (SaSS) • How Do Recommendation Engines Work? • Building a Movie Recommender using Collaborative Filtering in Python • Recommender Systems • Microsoft Best Practices on Recommendation Systems
9. Analytics Systems
10. Analytics API
11. Spec: APIs • Identify: who is the customer? • Track: what are they doing? • Page/Screen: what web page are they on?
12. Spec: Real Estate Events Property Searched User searched for properties Property List Viewed User viewed a property list or category Property List Filtered User filtered a property list or category Property Viewed User viewed a property details Property Favorited User favorited a property listing. etc … https://segment.com/academy/collecting-data/naming-conventions-for-clean-data/ The object-action framework
13. Spec: Real Estate Events (Example) Property Searched Fire this event when a visitor searches for properties. This event supports the following semantic properties: Property Type Description query String Query the user searched with
14. References • Segment • Jitsu (OSS) • RudderStack (OSS)