recommendation systems: applying amazon's collaborative filtering methods to e-commerce

40
Amazon Recommendation Services 123Mua.vn Recommendation Services Recommendation Services Nguyen.Cao-Duc Data Mining Team Lead E-Commerce & Services Dept. VNG Corp. Internal Research Document September 19, 2012

Upload: nguyen-cao

Post on 14-Apr-2017

119 views

Category:

Data & Analytics


0 download

TRANSCRIPT

Page 1: Recommendation Systems: Applying Amazon's Collaborative Filtering Methods to E-commerce

Amazon Recommendation Services 123Mua.vn Recommendation Services

Recommendation Services

Nguyen.Cao-Duc

Data Mining Team LeadE-Commerce & Services Dept.

VNG Corp.

Internal Research Document

September 19, 2012

Page 2: Recommendation Systems: Applying Amazon's Collaborative Filtering Methods to E-commerce

Amazon Recommendation Services 123Mua.vn Recommendation Services

Outline

1 Amazon Recommendation ServicesBusiness ModelResearch ModelImplementation Model

2 123Mua.vn Recommendation ServicesBusiness ModelImplementation Model

Page 3: Recommendation Systems: Applying Amazon's Collaborative Filtering Methods to E-commerce

Amazon Recommendation Services 123Mua.vn Recommendation Services

Business Model

Amazon Website

Page 4: Recommendation Systems: Applying Amazon's Collaborative Filtering Methods to E-commerce

Amazon Recommendation Services 123Mua.vn Recommendation Services

Business Model

Recommendation Services (cont.)

Browsing Product Recommendations:

Page 5: Recommendation Systems: Applying Amazon's Collaborative Filtering Methods to E-commerce

Amazon Recommendation Services 123Mua.vn Recommendation Services

Business Model

Recommendation Services (cont.)

Viewing Product Recommendations:

Page 6: Recommendation Systems: Applying Amazon's Collaborative Filtering Methods to E-commerce

Amazon Recommendation Services 123Mua.vn Recommendation Services

Business Model

Recommendation Services (cont.)

Purchasing Product Recommendations:

Page 7: Recommendation Systems: Applying Amazon's Collaborative Filtering Methods to E-commerce

Amazon Recommendation Services 123Mua.vn Recommendation Services

Business Model

Recommendation Services (cont.)

How to have such Recommendations:

Page 8: Recommendation Systems: Applying Amazon's Collaborative Filtering Methods to E-commerce

Amazon Recommendation Services 123Mua.vn Recommendation Services

Business Model

Recommendation Services (cont.)

Other Recommendations:

Page 9: Recommendation Systems: Applying Amazon's Collaborative Filtering Methods to E-commerce

Amazon Recommendation Services 123Mua.vn Recommendation Services

Research Model

Recommendation Problem

The main purpose of the recommendation system is torecommend personalized products to users of a merchant’sWeb site.

Two types of Recommendations:Content-based Filtering

Recommend items with similar content.Collaborative Filtering

Recommend items based on interests of a community ofusers.

Hybrid Content-based Collaborative FilteringCombination the two above approaches to overcome thedisadvantages of each approach.

Page 10: Recommendation Systems: Applying Amazon's Collaborative Filtering Methods to E-commerce

Amazon Recommendation Services 123Mua.vn Recommendation Services

Research Model

Content-based Recommendation

Page 11: Recommendation Systems: Applying Amazon's Collaborative Filtering Methods to E-commerce

Amazon Recommendation Services 123Mua.vn Recommendation Services

Research Model

Collaborative Filtering - Problem Description

Question: What should be the rating of Sam for Yellow?Approach: Use ratings of other users (user-based CF) orother items (item-based CF)

Page 12: Recommendation Systems: Applying Amazon's Collaborative Filtering Methods to E-commerce

Amazon Recommendation Services 123Mua.vn Recommendation Services

Research Model

How Collaborative Filtering works?

Page 13: Recommendation Systems: Applying Amazon's Collaborative Filtering Methods to E-commerce

Amazon Recommendation Services 123Mua.vn Recommendation Services

Research Model

Similarity Computation

Vector Cosine-based Similarity:Formular:

wu,v =

∑i∈I ru,i rv ,i√∑

i∈I r2u,i

√∑i∈I r2

v ,i

wi,j =

∑u∈U ru,i ru,j√∑

u∈U r2u,i

√∑u∈U r2

u,j

where:I is the set of items that both user u and v have rated.U is the set of users who rate both item i and i .Drawbacks

Different users have their own rating scales.

Page 14: Recommendation Systems: Applying Amazon's Collaborative Filtering Methods to E-commerce

Amazon Recommendation Services 123Mua.vn Recommendation Services

Research Model

Similarity Computation (cont.)

Correlation-based Similarity:Formular:

wu,v =

∑i∈I(ru,i − r̄u)(rv ,i − r̄v )√∑

i∈I(ru,i − r̄u)2√∑

i∈I(rv ,i − r̄v )2

wi,j =

∑u∈U(ru,i − r̄i)(ru,j − r̄j)√∑

u∈U(ru,i − r̄i)2√∑

u∈U(ru,j − r̄j)2

where:I is the set of items that both user u and v have rated.U is the set of users who rate both item i and i .

Page 15: Recommendation Systems: Applying Amazon's Collaborative Filtering Methods to E-commerce

Amazon Recommendation Services 123Mua.vn Recommendation Services

Research Model

Collaborative Recommendation

Given a user u:User-based prediction:

Aggregate the ratings of other users:

Pu,i = r̄u +

∑v∈V (rv ,i − r̄v )wu,v∑

v∈V |wu,v |

where V is the set of all users have rated the item iItem-based prediction:

Simple weighted average:

Pu,i =

∑n∈N ru,nwi,n∑

n∈N |wi,n|

where N is the set of other rated items of user u

Page 16: Recommendation Systems: Applying Amazon's Collaborative Filtering Methods to E-commerce

Amazon Recommendation Services 123Mua.vn Recommendation Services

Research Model

Collaborative Filtering - Drawbacks

User has to rate items to build profiles as well as item hasto be rated (cold-start problem: new user, new item, newsystem)Recommendations may not be diversed

Page 17: Recommendation Systems: Applying Amazon's Collaborative Filtering Methods to E-commerce

Amazon Recommendation Services 123Mua.vn Recommendation Services

Implementation Model

Recommendation Service Components

Page 18: Recommendation Systems: Applying Amazon's Collaborative Filtering Methods to E-commerce

Amazon Recommendation Services 123Mua.vn Recommendation Services

Implementation Model

Recommendation Service Components

Recommendation Service Components takes Items ofKnown Interest of the given User and Similar Items Table tocreate Recommendation Items.

Page 19: Recommendation Systems: Applying Amazon's Collaborative Filtering Methods to E-commerce

Amazon Recommendation Services 123Mua.vn Recommendation Services

Implementation Model

Recommendation Engine

Page 20: Recommendation Systems: Applying Amazon's Collaborative Filtering Methods to E-commerce

Amazon Recommendation Services 123Mua.vn Recommendation Services

Implementation Model

Recommendation Service Components (cont.)

Sources of Items of Known Interest with respect to a User:User shopping card activitiesUser purchasing activitiesUser favorite items profile (i.e WishList)

Popular items are items satisfied some pre-specified popularcriteria:

Number of item viewsTime on item viewNumber of item purchasings

Page 21: Recommendation Systems: Applying Amazon's Collaborative Filtering Methods to E-commerce

Amazon Recommendation Services 123Mua.vn Recommendation Services

Implementation Model

Recommendation Service Components (cont.)

Each cell in the Similar Items Table associates a commonalityindex (CI) to indicate the relatedness of that item with thepopular item. The relatedness of two items i , j could beexpressed via:

Two items have been purchased togetherTwo items have been rated similarly

or the value of wi,j =∑

u∈U (ru,i−r̄i )(ru,j−r̄j )√∑u∈U (ru,i−r̄i )2

√∑u∈U (ru,j−r̄j )2

or the similarity between two items using content-basedfilteringor . . . combinations of all above with some controlledparameters.

Page 22: Recommendation Systems: Applying Amazon's Collaborative Filtering Methods to E-commerce

Amazon Recommendation Services 123Mua.vn Recommendation Services

Implementation Model

Recommendation Service Components (cont.)

Similar lists are combined appropriately by a weightingscheme representing the relative importance of popularitems with respect to the items of known interests.Weighting scheme of similar item lists:

Rating of the user to the popular item.User purchased multiple copies of the popular itemTime user spend on the popular itemRecent purchasing items are weighted more than earlierpurchasing items

Page 23: Recommendation Systems: Applying Amazon's Collaborative Filtering Methods to E-commerce

Amazon Recommendation Services 123Mua.vn Recommendation Services

Implementation Model

Recommendation Service Components (cont.)

The combined sorted list of similar items lists may need bemodified to remove certain items:

Items already purchased or rated by user or have beenviewed by user and its content has not changed.Items not in any product groups registered by user.

The combined sorted list of similar items lists may need bemodified to add certain items:

Items user has considered to purchase but did notpurchase.Items user has viewed but its content has changed afterthat.

The recommendation result may be transfered to the enduser by different types of transmission methods (view onsite, email, mobile message, chat message, etc.)

Page 24: Recommendation Systems: Applying Amazon's Collaborative Filtering Methods to E-commerce

Amazon Recommendation Services 123Mua.vn Recommendation Services

Business Model

123Mua.vn Website

Page 25: Recommendation Systems: Applying Amazon's Collaborative Filtering Methods to E-commerce

Amazon Recommendation Services 123Mua.vn Recommendation Services

Business Model

Paid services

Page 26: Recommendation Systems: Applying Amazon's Collaborative Filtering Methods to E-commerce

Amazon Recommendation Services 123Mua.vn Recommendation Services

Business Model

Recommendation Services

Page 27: Recommendation Systems: Applying Amazon's Collaborative Filtering Methods to E-commerce

Amazon Recommendation Services 123Mua.vn Recommendation Services

Business Model

Pageview Traffic

Page 28: Recommendation Systems: Applying Amazon's Collaborative Filtering Methods to E-commerce

Amazon Recommendation Services 123Mua.vn Recommendation Services

Business Model

Pageview Traffic (cont.)

We want to have:

Page 29: Recommendation Systems: Applying Amazon's Collaborative Filtering Methods to E-commerce

Amazon Recommendation Services 123Mua.vn Recommendation Services

Implementation Model

Recommendation Engine

Page 30: Recommendation Systems: Applying Amazon's Collaborative Filtering Methods to E-commerce

Amazon Recommendation Services 123Mua.vn Recommendation Services

Implementation Model

Recommendation Engine (cont.)

Page 31: Recommendation Systems: Applying Amazon's Collaborative Filtering Methods to E-commerce

Amazon Recommendation Services 123Mua.vn Recommendation Services

Implementation Model

Items of Known Interest

Sources of Items of Known Interest with respect to a User:User category browsing or item viewing activitiesUser shopping card activities

Page 32: Recommendation Systems: Applying Amazon's Collaborative Filtering Methods to E-commerce

Amazon Recommendation Services 123Mua.vn Recommendation Services

Implementation Model

Popular Items

Page 33: Recommendation Systems: Applying Amazon's Collaborative Filtering Methods to E-commerce

Amazon Recommendation Services 123Mua.vn Recommendation Services

Implementation Model

Popular Items (cont.)

Popular items are items satisfied some pre-specified popularcriteria:

Number of page views on an item and/or category of theitem and/or shop of itemTime on an item and/or category of item and/or shop ofitemBounce Rate on that itemExit Rate on that item

Page 34: Recommendation Systems: Applying Amazon's Collaborative Filtering Methods to E-commerce

Amazon Recommendation Services 123Mua.vn Recommendation Services

Implementation Model

Popular Items (cont.)

Page 35: Recommendation Systems: Applying Amazon's Collaborative Filtering Methods to E-commerce

Amazon Recommendation Services 123Mua.vn Recommendation Services

Implementation Model

Similar Item List

Page 36: Recommendation Systems: Applying Amazon's Collaborative Filtering Methods to E-commerce

Amazon Recommendation Services 123Mua.vn Recommendation Services

Implementation Model

Similar Item List (cont.)

Sources of Similar Item List by targeting to certain itemsbased on:

Number of page views on an item and/or category of theitem and/or shop of itemTime on an item and/or category of item and/or shop ofitemBounce Rate on that itemExit Rate on that itemor items follow certain business objectives such as itemsis Up within a period of time.

Sources of Similar Item List with respect to a Popular item:Items of the same category and/or shop

Page 37: Recommendation Systems: Applying Amazon's Collaborative Filtering Methods to E-commerce

Amazon Recommendation Services 123Mua.vn Recommendation Services

Implementation Model

Similar Item List (cont.)

Each item in the Similar Item List associates a commonalityindex (CI) to indicate the relatedness of that item with thepopular item. The relatedness of two items i , j could beexpressed via:

The value of wi,j =∑

u∈U (ru,i−r̄i )(ru,j−r̄j )√∑u∈U (ru,i−r̄i )2

√∑u∈U (ru,j−r̄j )2

where:ru,i represents interest level of user u towards item ior the similarity between two items using content-basedfilteringor . . . combinations of all above with some controlledparameters.

Page 38: Recommendation Systems: Applying Amazon's Collaborative Filtering Methods to E-commerce

Amazon Recommendation Services 123Mua.vn Recommendation Services

Implementation Model

Weighting Scheme of Similar Item Lists

Similar item lists are combined appropriately by aweighting scheme representing the relative importance ofpopular items with respect to the items of known interests.Weighting scheme of similar item lists of popular items:

User views the popular item multiple timesTime user spent on the popular itemRecent viewings of popular items weighted more

Page 39: Recommendation Systems: Applying Amazon's Collaborative Filtering Methods to E-commerce

Amazon Recommendation Services 123Mua.vn Recommendation Services

Implementation Model

Question

How to identify popular topics from multiplerelated/independent properties?How to measure the interest of a topic viewed by a user?

Page 40: Recommendation Systems: Applying Amazon's Collaborative Filtering Methods to E-commerce

Amazon Recommendation Services 123Mua.vn Recommendation Services

Implementation Model

THANK YOU *-*