Difference between revisions of "Recommendation"
(→Recommender Systems) |
|||
| Line 18: | Line 18: | ||
* ... no, have a very large dataset, then [[Alternating Least Squares (ALS)]] | * ... no, have a very large dataset, then [[Alternating Least Squares (ALS)]] | ||
* ... no, have small to medium dataset, then [[Matrix Factorization]] | * ... no, have small to medium dataset, then [[Matrix Factorization]] | ||
| + | |||
| + | |||
| + | * [http://medium.com/@srnghn/machine-learning-trying-to-make-recommendations-ea2912cf468 Machine Learning: Trying to make recommendations | Stacey Ronaghan - Medium] | ||
Revision as of 21:31, 23 October 2019
Youtube search... ...Google search
- Capabilities
- Clustering
- AI Solver
- Collaborative Filtering | Wikipedia
- Personalized Marketing | Wikipedia
Can items can be directly related to users?
- ... yes, K-Nearest Neighbors (KNN)
- ... no, have a very large dataset, then Alternating Least Squares (ALS)
- ... no, have small to medium dataset, then Matrix Factorization
systems examine attributes of the items recommended. For example, if a Netflix user has watched many cowboy movies, then recommend a movie classified in the datastore as having the “scifi” genre.
systems recommend items based on similarity measures between users and/or items. The items recommended to a user are those preferred by similar users.
Contents
Recommender Systems
- Recommender System | Wikipedia
- Recommendation System Algorithms | Daniil Korbut
- Business Intelligence Through Intellectual Property Analytics – Examining Facebook and Amazon | Valuenex
- Recommendation Systems | Stanford InfoLab
- Introduction To Recommendation system In Javascript | Oni Stephen - Medium
Grouping related items together without labeling them, e.g. grouping patient records with similar symptoms without knowing their symptoms
Building Recommendation Systems in Azure
- Microsoft Azure
Azure Machine Learning Studio: Matchbox Recommender
Cortana Analytics: Building a recommendations model
