Recommender Systems

Get Started. It's Free
or sign up with your email address
Rocket clouds
Recommender Systems by Mind Map: Recommender Systems

1. Domain

1.1. Content

1.1.1. News, information, text

1.1.2. Products, vendors, bundles

1.1.3. Matchmaking (other people)

1.1.4. Sequencies

1.1.4.1. e.g. music playlists

1.2. Novelty

1.2.1. new items

1.2.1.1. e.g. movies, books

1.2.2. re-recommend old ones

1.2.2.1. e.g. groceries, music

2. Purpose

2.1. recommendation itself

2.1.1. sales

2.1.2. information

2.2. education of user/customer

2.2.1. e.g. OWL tips

2.3. build community of users around products or content

2.3.1. e.g. TripAdvisor

3. Recommendation context

3.1. What is the User doing at the time of recommendation?

3.1.1. shopping

3.1.2. listening to music

3.1.3. hanging out with other people

3.2. How does the context constrain the recommender?

3.2.1. Groups

3.2.2. Automatic consumption (vs. suggestion)

3.2.3. Level of attention

3.2.3.1. Level of interruption

4. Whose Opinions

4.1. Experts

4.2. Ordinary "phoaks"

4.2.1. People Helping One Another Know Stuff

4.3. People like you

5. Personalization Level

5.1. Generic/Non-personalized

5.1.1. everyone receives same recommendations

5.2. Demographic

5.2.1. matches the target group

5.3. Ephemeral

5.3.1. matches current actitivity

5.4. Persistent

5.4.1. matches long-term interest

6. Privacy and Trustworthiness

6.1. Who knows what about me?

6.1.1. Personal information revealed

6.1.2. Identity

6.1.3. Deniability of preferences

6.2. Is the recommendation honest?

6.2.1. biases built-in by operator

6.2.1.1. "business rules"

6.2.2. vulnerability to external manipulation

6.2.3. transparency of "recommenders"

6.2.3.1. reputation

7. Interfaces

7.1. Types of output

7.1.1. predictions

7.1.2. recommendations

7.1.3. filtering

7.1.4. organic vs. explicit presentation

7.1.4.1. agent/discussion interface

7.2. Types of input

7.2.1. Explicit

7.2.2. Implicit

8. Recommendation Algorithms

8.1. Non-personalized summary statistics

8.2. Content-based filtering

8.2.1. Information filtering

8.2.1.1. Knowledge-based

8.3. Collaborative filtering

8.3.1. User-user

8.3.1.1. Item-item

8.3.1.1.1. Dimensionality reduction

8.4. Others

8.4.1. Critique / Interview-based recommendations

8.4.1.1. Hybrid Techniques