16
1 Recommendation & Advertising in e-commerce Quan Yuan

Invited talk on Recommendation and Advertising in Alibaba, RecSys'13

Embed Size (px)

DESCRIPTION

Invited talk on Recommendation and Advertising in Alibaba, RecSys'13

Citation preview

Page 1: Invited talk on Recommendation and Advertising in Alibaba, RecSys'13

1

Recommendation &

Advertising in e-commerce

Quan Yuan

Page 2: Invited talk on Recommendation and Advertising in Alibaba, RecSys'13

Agenda

• Recommendation – Item-based

– User-based

• Recommendation in Ads Targeting – Look-alike Targeting

– Ctx-weather Targeting

– User Profiling • FM for Purchasing power prediction

• Life-stage modeling

Page 3: Invited talk on Recommendation and Advertising in Alibaba, RecSys'13

Alibaba in China

1st B2C

1st C2C

1st Group-buy site

1st Price-comparison

1st Shopping App

$30B usd 11.11,2012

100+ online scenarios for Recommendation

10% of GMV (daily trading volume) comes from Recommender System Alibaba is a platform, to help sellers’ selling.

Page 4: Invited talk on Recommendation and Advertising in Alibaba, RecSys'13

Item-based Rec

• Item-Item Relevance Model – 10+ relevance model based on: click, buy, search, bookmark, content, etc.

– Different granularity: session/day/week/month/year

– Offline computation, PB size, 19min

• Similar VS. Complementary – P( buy | user, item, ctx)

– Similar only is good for

CTR but harm for CVR

机密文档

Similar Reco

Complementary Reco

Page 5: Invited talk on Recommendation and Advertising in Alibaba, RecSys'13

User-based Rec

• “Products you may like”

• Brand Rec @Tmall

40+%CVR; 50%+GMV Lift VS. Popular

MostPopular : Red BrandRec: Blue

Rec is good for long-tail brands

Page 6: Invited talk on Recommendation and Advertising in Alibaba, RecSys'13

Agenda

• Recommendation – Item-based

– User-based

• Recommendation in Ads Targeting – Look-alike Targeting

– Ctx-weather Targeting

– User Profiling • FM 4 Purchasing power prediction

• Life-stage modeling

Page 7: Invited talk on Recommendation and Advertising in Alibaba, RecSys'13

Ads Platform

1st B2C

1st C2C

1st Group-buy site

1st Price-comparison

1st Shopping App

$30B usd 11.11,2012

1st Ads Platform

Taobao Ads Network & Exchange (TANX)

External Publisher Video/News/Apps...

Page 8: Invited talk on Recommendation and Advertising in Alibaba, RecSys'13

Display Ads Targeting

Coverage

Performance

Behavioral Targeting

Contextual Targeting

Re-targeting

Demographic Targeting

Look-Alike Targeting

After the targeting(matching), we adopt the ranking to optimize CTR/CVR

Page 9: Invited talk on Recommendation and Advertising in Alibaba, RecSys'13

Rec for Ads

Coverage

Performance

Behavioral Targeting

Contextual Targeting

Re-targeting

Demographic Targeting

Look-Alike Targeting

ItemCF

ItemCF

UserCF

ContentRec

WeatherRec

FM for Purchase Power Modeling

Life-Stage Modeling

Page 10: Invited talk on Recommendation and Advertising in Alibaba, RecSys'13

Look-alike Targeting

Page 11: Invited talk on Recommendation and Advertising in Alibaba, RecSys'13

Contextual Engine

Weather-based Ads

PM2.5

Temp.

Climate

Wind

Ads Trigger

CTR & click value both improved than popular! In mobile ads, it is hard to track users behavior

Page 12: Invited talk on Recommendation and Advertising in Alibaba, RecSys'13

User-Cat Consumption Matrix

I 1 I2 I3 I4

U1 ? 0 21 1

U2 9 ? 1 0

U3 0 ? 6 11

U4 19 0 2 ?

User Consumption Matrix

• User-Category Amount Matrix

Page 13: Invited talk on Recommendation and Advertising in Alibaba, RecSys'13

Sample: Purchasing Prediction Model

Global Bias

0.9574

User Bias

0.9132

Cat Bias

0.8868 Cross-Cat

0.8729

Indicator-Cat

0.8681 100M x 100K Matrix Factorization on a single server

Page 14: Invited talk on Recommendation and Advertising in Alibaba, RecSys'13

Life-stage Modeling

• Using multiple behavioral data (buy, view, search, etc.) and split the data as sequence

Current

The baby will be

one year old at

6-12 month 1-6 month 1-6 month pregnancy

Page 15: Invited talk on Recommendation and Advertising in Alibaba, RecSys'13

Life-stage Modeling cont.

• Given an observed behavioral sequence x=(x1...xl), our task is to predicts a life stage sequence y=(y1...yl)

Sequence of behavioral

Sequence of Life-stage

y1 y2 y3

x1 x2 x3

y4 y5 y6

x4 x5 x6

Page 16: Invited talk on Recommendation and Advertising in Alibaba, RecSys'13

16

Thanks &

We are Hiring~! “A-Star” for Top Talents http://campus.alibaba.com/

[email protected]

Sina weibo: 袁全V