8
Collaborative Filtering Zaffar Ahmed

Zaffar+Ahmed+ +Collaborative+Filtering

Embed Size (px)

Citation preview

Page 1: Zaffar+Ahmed+ +Collaborative+Filtering

Collaborative Filtering

Zaffar Ahmed

Page 2: Zaffar+Ahmed+ +Collaborative+Filtering

Overview

• It analyzes data which relies on using data from numerous sources to develop profiles of people who are related with similar tastes and spending habits.

• It is based on ‘word-of-mouth’ idea

• Gives reliable recommendations

Page 3: Zaffar+Ahmed+ +Collaborative+Filtering

Mechanism behind Collaborative Filtering

• Users preferences are registered• Similarity metric vector is used and users are

found whose preferences are similar• A weighted average of preferences is

calculated• Resulting preference function is used for

recommendations

Page 4: Zaffar+Ahmed+ +Collaborative+Filtering

Facts

• It needs a lot of stored data for reliable recommendations for the active user.

• Bigger population – more useful and effective recommendations will be produced (Smart Mobs)

• Small data – shows false connections or poor predictions of active user tastes

• Suffers from cold start problem – database needs to be populated first.

Page 5: Zaffar+Ahmed+ +Collaborative+Filtering

Types of Collaborative Filtering

•Memory-based: uses user rating data to compute similarity between users or items–Neighborhood-based CF

– calculates similarity b/w two users or items, produces a prediction for the active user taking the weighted average of all the ratings.

–Item/user based top-N recommendations–identifies the K most similar users using similarity based vector model.

–Locality sensing hashing: It implements nearest neighbor mechanism in linear time.

Advantages: 1) explainability of the results, 2) easy to create and use, 3) new data can be added easily

and incrementally

2) Disadvantages: 1) depends on human rating, 2) performance decreases when data gets sparse, 3) it can not handle new users or items

Page 6: Zaffar+Ahmed+ +Collaborative+Filtering

Types of Collaborative Filtering•Model-based: models (ontologies) are developed using data mining, machine learning algorithms to find patterns based on training data. It has more holistic goal to uncover latent factors that explain observed ratings. •Bayesian Networks•Clustering models•Latent semantic models

Advantages–Handles sparsity better than memory based algos: improves scalability and prediction performance.

Disadvantages–Expensive model building

Page 7: Zaffar+Ahmed+ +Collaborative+Filtering

Types of Collaborative Filtering

• Hybrid – Combines model-based and memory-based CF algos.– overcomes the limitations of native CF approaches.

Advantages• Improves prediction performance

Disadvantages• Increased complexity• Expensive to implement

Page 8: Zaffar+Ahmed+ +Collaborative+Filtering

Thank you