behavioral targeting
TRANSCRIPT
![Page 1: Behavioral targeting](https://reader033.vdocuments.us/reader033/viewer/2022052908/559706f61a28ab932f8b4581/html5/thumbnails/1.jpg)
How much can Behavioral Targeting Help Online Advertising?
Jun Yan, Ning Liu, Gang Wang, Wen Zhang, YunJiang, Zheng Chen, WWW 2009
Advisor: Chia-Hui Chang
Student: Kuan-Hua Huo
Date: 2010-09-07
1
![Page 2: Behavioral targeting](https://reader033.vdocuments.us/reader033/viewer/2022052908/559706f61a28ab932f8b4581/html5/thumbnails/2.jpg)
Outline
1. Introduction
2. Behavioral Targeting
3. Experiment Configuration
4. BT Results
5. Conclusions
2
![Page 3: Behavioral targeting](https://reader033.vdocuments.us/reader033/viewer/2022052908/559706f61a28ab932f8b4581/html5/thumbnails/3.jpg)
Instruction
• Behavioral Targeting (BT)– BT uses information collected on an individual's
web-browsing behavior,• such as the pages they have visited or
• the searches they have made,
– to select which advertisements to display to that individual.
– Practitioners believe this helps them deliver their online advertisements to the users who are most likely to be influenced by them.
3
![Page 4: Behavioral targeting](https://reader033.vdocuments.us/reader033/viewer/2022052908/559706f61a28ab932f8b4581/html5/thumbnails/4.jpg)
How much can BT help online advertising?
• Does BT truly have the ability to help online advertising?
• How much can BT help online advertising using commonly used evaluation metrics?
• What BT strategy works better than others for ads delivery?
4
![Page 5: Behavioral targeting](https://reader033.vdocuments.us/reader033/viewer/2022052908/559706f61a28ab932f8b4581/html5/thumbnails/5.jpg)
Does BT truly have the ability to help online advertising?
• Users have similar search or browsing behaviors– similar interests
– higher probability to click the same ad
• Online users can be grouped into different user segments according to their behaviors– within- and between- ads user similarities
– the users who clicked the same ad can be over 90 times more similar than the users who clicked different ads.
5
![Page 6: Behavioral targeting](https://reader033.vdocuments.us/reader033/viewer/2022052908/559706f61a28ab932f8b4581/html5/thumbnails/6.jpg)
How much can BT help online advertising using commonly used evaluation metrics?
• We propose to observe
– how much BT can improve ads CTR
– through the segmentation of users into a number of small groups for targeted ads delivery.
• Through studying ads CTR
– before and after user segmentation for ads delivery
– ads CTR can be improved by as much as 670% over all the ads we collected.
6
![Page 7: Behavioral targeting](https://reader033.vdocuments.us/reader033/viewer/2022052908/559706f61a28ab932f8b4581/html5/thumbnails/7.jpg)
What BT strategy works better than others for ads delivery?
• According to the definition of “Behavioral Targeting (BT)”, there are two strategies to represent the users’ behavior– Web browsing behavior => users’ clicked pages– Search behavior => search queries
• we draw the conclusion that – user search queries can perform several times better
than user browsing behavior– tracking the short term user behaviors are more
effective than tracking the long term user behaviors
7
![Page 8: Behavioral targeting](https://reader033.vdocuments.us/reader033/viewer/2022052908/559706f61a28ab932f8b4581/html5/thumbnails/8.jpg)
Behavioral Targeting
• To represent user behavior by their page-views
– We consider the clicked URLs of search users as their profiles
– All the users can be considered as a user-by-URL matrix
• The classical Term Frequency Inverse Document Frequency (TFIDF) indexing
– each user as a document and each URL as a term
8
![Page 9: Behavioral targeting](https://reader033.vdocuments.us/reader033/viewer/2022052908/559706f61a28ab932f8b4581/html5/thumbnails/9.jpg)
Behavioral Targeting cont.
• Mathematically, all users are represented by a real valued matrix
– g is the total number of users
– l is the total number of URLs
• A user is a row of U,
– a real valued vector
– with the weight for each entry to be,
9
![Page 10: Behavioral targeting](https://reader033.vdocuments.us/reader033/viewer/2022052908/559706f61a28ab932f8b4581/html5/thumbnails/10.jpg)
Behavioral Targeting cont.
• We build the user behavioral profile by – all terms that appear in a user’s queries as his
previous behaviors.
• We can represent each user in the Bag of Words (BOW) model – each term is considered as a feature.
– each user is represented by BOW with corresponding term frequency
• We use the same TFIDF indexing10
![Page 11: Behavioral targeting](https://reader033.vdocuments.us/reader033/viewer/2022052908/559706f61a28ab932f8b4581/html5/thumbnails/11.jpg)
Behavioral Targeting cont.
• Two different BT strategies– The long term user behavior (7 days’ user behavior) – The short term user behavior (1 day’s user behavior)
• Validate and compare four different BT Strategies– 1. LP: using Long term user behavior all through the
seven days and representing the user behavior by Page-views; – 2. LQ: using Long term user behavior all through the seven
days and representing the user behavior by Query terms; – 3. SP: using Short term user behavior (1 day) and
representing user behavior by Page-views; – 4. SQ: using Short term user behavior (1 day) and
representing user behavior by Query terms.
11
![Page 12: Behavioral targeting](https://reader033.vdocuments.us/reader033/viewer/2022052908/559706f61a28ab932f8b4581/html5/thumbnails/12.jpg)
Experiment Configuration
1. Symbols and Experiment Setup – which will be used throughout the experiments
– with detailed experiment configurations
2. Evaluation Metrics– Within- and Between- Ads User Similarity
– Ads Click-Through Rate
– F-measure
– Ads Click Entropy
12
![Page 13: Behavioral targeting](https://reader033.vdocuments.us/reader033/viewer/2022052908/559706f61a28ab932f8b4581/html5/thumbnails/13.jpg)
Symbols and Experiment Setup
• be the set of the n advertisements in our dataset
• For each ad 2 , suppose 7 183+84+-are all the queries which have displayed or clicked 2 .
• Suppose the group of users who have either displayed or clicked 2 is represented by
13
![Page 14: Behavioral targeting](https://reader033.vdocuments.us/reader033/viewer/2022052908/559706f61a28ab932f8b4581/html5/thumbnails/14.jpg)
Symbols and Experiment Setup cont.
• We define a Boolean function,
– to show whether the user has clicked ad
• BT aims to group users into segments of similar behaviors
– k-means and CLUTO for user segmentation14
![Page 15: Behavioral targeting](https://reader033.vdocuments.us/reader033/viewer/2022052908/559706f61a28ab932f8b4581/html5/thumbnails/15.jpg)
Symbols and Experiment Setup cont.
• The users are segmented into K segments according to their behaviors
– To represent the distribution of under a given user segmentation results
– where H stands for all the users in who are grouped into the kth user segment
– the kth user segment be represented by
15
![Page 16: Behavioral targeting](https://reader033.vdocuments.us/reader033/viewer/2022052908/559706f61a28ab932f8b4581/html5/thumbnails/16.jpg)
Evaluation Metrics
• Within- and Between- Ads User Similarity
– The similarity between a pair of users and is OMN
– the classical Cosine similarity can be utilized for the similarity computation between users
16
![Page 17: Behavioral targeting](https://reader033.vdocuments.us/reader033/viewer/2022052908/559706f61a28ab932f8b4581/html5/thumbnails/17.jpg)
Evaluation Metrics cont.
• For ad 2 , the user similarity, who clicked it, is defined as the within ads user similarity
– where [ ;< = is the number of users who clicked ad 2
• The between ads user similarity as
17
![Page 18: Behavioral targeting](https://reader033.vdocuments.us/reader033/viewer/2022052908/559706f61a28ab932f8b4581/html5/thumbnails/18.jpg)
Evaluation Metrics cont.
• We further define a ratio between
OS2 and O\ as
• A large R score means the two ads have – a large within ads similarity
– small between ads similarity
– the more confident we are on the basic assumption of BT
18
![Page 19: Behavioral targeting](https://reader033.vdocuments.us/reader033/viewer/2022052908/559706f61a28ab932f8b4581/html5/thumbnails/19.jpg)
Ads Click-Through Rate
• The CTR of ad 2 is defined as
• After user segmentation, the CTR of 2 over user segment H is
– where RHR is the number of users in H
19
![Page 20: Behavioral targeting](https://reader033.vdocuments.us/reader033/viewer/2022052908/559706f61a28ab932f8b4581/html5/thumbnails/20.jpg)
F-measure
• A user segment H ,
– satisfies that
– a segment of users who are more interested in ad 2 than other users
– only validate the precision of BT strategies in finding potentially interested users
• Precision and Recall are defined as
• the classical F-measure for results evaluation
20
![Page 21: Behavioral targeting](https://reader033.vdocuments.us/reader033/viewer/2022052908/559706f61a28ab932f8b4581/html5/thumbnails/21.jpg)
Ads Click Entropy
• Define the ads click Entropy to show the effectiveness of different BT strategies
• For ad 2 the probability of users in segment H , who will click this ad, is estimated by
• we define the ads click Entropy of ad 2 as
21
![Page 22: Behavioral targeting](https://reader033.vdocuments.us/reader033/viewer/2022052908/559706f61a28ab932f8b4581/html5/thumbnails/22.jpg)
BT Results
• Assumption of BT– show its potential in helping online advertising
• BT for Online Advertising– show how much BT can improve ads CTR
• More Evaluation– More evaluated results by the ads click Entropy
and F-measure
22
![Page 23: Behavioral targeting](https://reader033.vdocuments.us/reader033/viewer/2022052908/559706f61a28ab932f8b4581/html5/thumbnails/23.jpg)
Assumption of BT
• The average within ads user similarity over all ads
• The average between ads user similarity over all ads
• The averaged ratio
23
![Page 24: Behavioral targeting](https://reader033.vdocuments.us/reader033/viewer/2022052908/559706f61a28ab932f8b4581/html5/thumbnails/24.jpg)
Assumption of BT cont.
• Within- and between- ad user similarity.
– the within ads similarity of users, which are represented by SQ, can be around 90 times larger than the corresponding between ads similarity.
– 99.37% pairs of ads in our dataset have the property that
24
![Page 25: Behavioral targeting](https://reader033.vdocuments.us/reader033/viewer/2022052908/559706f61a28ab932f8b4581/html5/thumbnails/25.jpg)
Assumption of BT cont.
• To validate whether the difference between OS and O is statistically significant, we implement the paired t-test to compare the results of OS with that of \ .
• The t-test results of different BT strategies, which are all less than 0.05.
25
![Page 26: Behavioral targeting](https://reader033.vdocuments.us/reader033/viewer/2022052908/559706f61a28ab932f8b4581/html5/thumbnails/26.jpg)
BT for Online Advertising
• Group all our users into 20, 40, 80 and 160 clusters
• Calculate `a2 over all users
• Calculate its CTR over different user segments, i.e. `a2R
• A user segment that have the highest CTR for
26
![Page 27: Behavioral targeting](https://reader033.vdocuments.us/reader033/viewer/2022052908/559706f61a28ab932f8b4581/html5/thumbnails/27.jpg)
BT for Online Advertising cont.
• the CTR improvement degree of ad 2
• The average results, i.e. improvement
• T-test of CTR improvements by BT
27
![Page 28: Behavioral targeting](https://reader033.vdocuments.us/reader033/viewer/2022052908/559706f61a28ab932f8b4581/html5/thumbnails/28.jpg)
More Evaluation
• The worst case
– suppose we have K user segments, the users who clicked the same ad uniformly distribute
• Ads click Entropy results
28
![Page 29: Behavioral targeting](https://reader033.vdocuments.us/reader033/viewer/2022052908/559706f61a28ab932f8b4581/html5/thumbnails/29.jpg)
F-measure of different BT strategies
29
![Page 30: Behavioral targeting](https://reader033.vdocuments.us/reader033/viewer/2022052908/559706f61a28ab932f8b4581/html5/thumbnails/30.jpg)
BT for Online Advertising cont.
• we present the scatter plot of the precision and recall over all the ads
30
![Page 31: Behavioral targeting](https://reader033.vdocuments.us/reader033/viewer/2022052908/559706f61a28ab932f8b4581/html5/thumbnails/31.jpg)
Conclusion
1. The users who clicked the same ad will be more similar than the users who clicked different ads;
2. Ads CTR can be averagely improved as high as 670% over all the ads we collected if we directly adopt the most fundamental user clustering algorithms for BT;
3. For the user representation strategies, which are defined in the definition of BT, tracking the short term user search behavior can perform better than tracking the long term user browsing behavior.
31
![Page 32: Behavioral targeting](https://reader033.vdocuments.us/reader033/viewer/2022052908/559706f61a28ab932f8b4581/html5/thumbnails/32.jpg)
32