Computational Advertising has been an important topical area in information retrieval and knowledge management. This tutorial will be focused on real-time advertising, aka Real-Time Bidding (RTB), the fundamental shift in the field of computational advertising. It is strongly related to CIKM areas such as user log analysis and modelling, information retrieval, text mining, knowledge extraction and management, behaviour targeting, recommender systems, personalization, and data management platform. This tutorial aims to provide not only a comprehensive and systemic introduction to RTB and computational advertising in general, but also the emerging research challenges and research tools and datasets in order to facilitate the research. Compared to previous Computational Advertising tutorials in relevant top-tier conferences, this tutorial takes a fresh, neutral, and the latest look of the field and focuses on the fundamental changes brought by RTB. We will begin by giving a brief overview of the history of online advertising and present the current eco-system in which RTB plays an increasingly important part. Based on our field study and the DSP optimisation contest organised by iPinyou, we analyse optimization problems both from the demand side (advertisers) and the supply side (publishers), as well as the auction mechanism design challenges for Ad exchanges. We discuss how IR, DM and ML techniques have been applied to these problems. In addition, we discuss why game theory is important in this area and how it could be extended beyond the auction mechanism design. CIKM is an ideal venue for this tutorial because RTB is an area of multiple disciplines, including information retrieval, data mining, knowledge discovery and management, and game theory, most of which are traditionally the key themes of the conference. As an illustration of practical application in the real world, we shall cover algorithms in the iPinyou global DSP optimisation contest on a production platform; for the supply side, we also report experiments of inventory management, reserve price optimisation, etc. in production systems. We expect the audience, after attending the tutorial, to understand the real-time online advertising mechanisms and the state of the art techniques, as well as to grasp the research challenges in this field. Our motivation is to help the audience acquire domain knowledge and obtain relevant datasets, and to promote research activities in RTB and computational advertising in general.

1. Real-Time Bidding
A New Frontier of Computational Advertising Research
Jun Wang and Shuai Yuan, University College London
Xuehua Shen, iPinyou
Samuel Seljan, AppNexus

2. About us
• Dr Jun Wang and Shuai Yuan from University
College London
– Media future research group
– Computational advertising (big data analytics
and web economics)
• Dr Jun Wang is a Senior Lecturer (Associate
Professor) of Department of Computer Science,
UCL
• Shuai Yuan is Jun’s PhD student in CRS
(completing research status)
2

3. About us contd.
• Dr Xuehua Shen is CTO and co-founder of
iPinYou
– He received his PhD of Computer Science at
University of Illinois at Urbana-Champaign,
USA
iPinYou is the largest Demand Side Platform (DSP) and the leader of audience
targeting and real-time advertising in China. It makes intelligent decision for more
than 3 billion ads impressions each day. In the past two years, iPinYou is the pioneer
of programmatic buying of display media in China and organizes the annual RTB
Summit. It has more than 150 employees and is headquartered in Beijing and has
offices in Shanghai, Guangzhou, and Silicon Valley.
3

4. About us contd.
• Dr Samuel Seljan is a Quantitative Analyst at AppNexus
– Supply-side optimization
• to improve the allocation of impressions across RTB and non-RTB markets
• reserve price optimization
– He obtained a PhD in Political Science from the University of California, San
Diego
• AppNexus is one of the largest real-time advertising platforms (exchanges)
– Offers one of the most powerful, open and customizable advertising technology
platforms
– Serves Microsoft Advertising Exchange, Interactive Media (Deutsche Telekom),
and Collective Exchange
4

5. •
The background of RTB (25min)
Outline
– history, glossaries, fundamental challenges, players and their objectives
•
An empirical study of RTB auctions (15min)
– periodic features, bids’ distribution, daily pacing, frequency & recency control
•
Demand side optimisation (40min)
– bidding algorithms, conversion attribution
•
The iPinyou global bidding algorithm competition (30min, break 30min)
– results, prizes, how to participate
•
Supply side optimisation (40min)
– ad density, reserve prices, revenue channel selection, bid landscape
forecasting, pricing guaranteed delivery, data leakage
•
Financial methods in computational advertising (15min)
– game theory basic, ad options
•
Panel discussion (15min)
5

6. Part 1: The background of RTB
• Egyptians used papyrus to make sales
messages and wall posters (4000 BCE)
• In the 18th century, ads started to appear
in weekly newspapers in England
• Thomas J. Barratt has been called "the
father of modern advertising"
1806
1900
courtesy of Wikipedia
1890
1952
6

7. Ads can be not annoying
courtesy of lostateminor.com
7

8. Glossaries
• Real-Time Bidding is an important aspect of Programmatic buying, which is
getting more and more popular in Display (related) advertising. Another
major part of Online advertising is Sponsored search
• An Impression is an ad display opportunity which generates when a User
visits a webpage containing ad Placements
• The Publisher sends a bid request of this impression to an Ad network, or an
Ad exchange via his Supply side platform (SSP), then to Demand side
platforms (DSP) to reach Advertisers
• Usually, DSPs contact Data management platform (DMP) to check the
Segments of the current user, i.e., his intents or interests. Then a bid will be
computed for the Campaign
• The payment among these entities is usually in Cost per mille (CPM), but
sometimes could be Cost per click (CPC) or Cost per acquisition (CPA)
• If the advertiser wins the impression, his Creative will be displayed to the
user
8

9. The fundamental challenges
• To find the best match between a given user in a given context and a
suitable advertisement?
• To achieve the best campaign performance (e.g., ROI) within the budget
constraint?
• To generate the most revenue given the traffic and demand?
• To maintain a healthy environment so that users get less annoyed (both
quality and quantity)?
Computational advertising, AZ Border, 2008
Dynamics of bid optimization in online advertisement auctions, C Borges et al. 2007
Dynamic revenue management for online display advertising, G Roels and K Fridgeirsdottir, 2009
Advertising in a pervasive computing environment, A Ranganathan and RH Campbell, 2002
9

10. The simplified history of online (display) advertising
Real-time Bidding for Online Advertising: Measurement and Analysis, S Yuan et al., 2013
10

11. Direct sales
• Advertisers and publishers
talk to (4A) agencies
• Still popular in today’s
marketplace
27th Oct 1994, AT & T on HotWired.com
(78% CTR)
courtesy of Ad Age
11

12. Trading in ad networks
Why?
• After direct sales, some impressions
will remain unsold (remnants)
• Small publishers cannot find buyers
directly
Ad networks are first-level aggregators
of (long-tail) demand and supply.
courtesy of Admeld
12

13. Introducing the ad exchange
single ad network is easy
courtesy of www.liesdamnedlies.com
a few ad networks are manageable
hundreds of ad networks are nightmare
13

14. A video
courtesy of Internet advertising bureau, src: http://www.youtube.com/v/1C0n_9DOlwE
14

15. Introducing the ad exchange contd.
• Ad exchanges are
marketplaces
• Advertisers and
publishers have to rely
on tools to connect
• Real-Time Bidding
promotes user-oriented
bidding
Ad exchanges are second-level aggregators of demand and supply
15

16. The complex display ad eco-system
courtesy of LUMAscape 2011
16

17. A new picture in 2013
Demand side
courtesy of Rare Crowd
Aggregators
Supply side
17

18. Boundaries are getting blurry
Google is introducing display ads to search result pages
courtesy of Google
18

19. Introducing the Demand Side Platform (DSP)
• To connect to ad exchanges and SSPs
• To buy user-data from DMPs
• To provide campaign management
functions
• To bid by targeting rules and
optimisation algorithms
• To report and analyse the performance
A demand side platform (DSP), also called buy side optimizer and buy side
platform is a technology platform that provides centralized and aggregated
media buying from multiple sources including ad exchanges, ad networks and
sell side platforms, often leveraging real time bidding capabilities of these
sources.
IAB Wiki
courtesy of LUMAscape 2011
19

20. DSP contd.
Bidding
algorithm is
the core of a
DSP
20

21. Introducing the Supply Side Platform (SSP)
• To upload advertisements and rich media
• To traffick ads according to differing business
rules
• To target ads to different users, or content
• To tune and optimise
• To report impressions, clicks, post-click &
post-impression activities, and interaction
metrics
A sell side platform (SSP), also called sell side optimizer,
inventory aggregator, and yield optimizer is a technology
platform that provides outsourced media selling and ad network
management services for publishers.
IAB Wiki
courtesy of LUMAscape 2011
21

22. SSP contd.
Yield
optimisation
is the core
of a SSP
22

23. Introducing the Data Management Platform (DMP)
• To collect users’ online behaviour data across
websites
(Mainly via 3rd party cookies)
• To predict users’ segments (intents/interests)
bases on online behaviour data
• To answer the query of users’ segments
• To provide audience profiling and expansion
services
A Data Management Platform (DMP) is a system that allows
the collection of audience intelligence by advertisers and
ad agencies, thereby allowing better ad targeting in
subsequent campaigns.
IAB Wiki
courtesy of LUMAscape 2011
23

24. DMP contd.
The user base and the
learning engine are the cores
of a DMP
24

25. Behind the banner
cmsummit.com/behindthebanner
Behind the banner
(A visualization of the adtech ecosystem)
Adobe, 2013
25

26. Part 2: An empirical study of RTB
• To understand the bidding behaviours in RTB auctions
• To present some research challenges
• To help to get familiar with RTB in the real-world
• The data is from production DSP & SSP based in UK
– 52m impressions, 72k clicks, and 37k conversions from Feb to May 2013
• Started from convs/clicks and back-traced to imps
– 12m auctions from 50 placements from Dec 2012 to May 2013
• 16 websites of different categories
26

27. Periodic patterns
The numbers of imp (left) and click (right) both show
strong daily and weak weekly patterns,
corresponding to the normal human activity
27

28. Periodic patterns contd.
Daily periodic patterns for conv (left) and cvr (right) show that
people are less likely to convert during late night
28

29. Frequency distribution
The frequency against CVR plot from two different campaigns
Campaign 1 sets a frequency cap of 2-5 -> poor performance
Campaign 2 sets a frequency cap of 6-10 -> waste of budget
29

30. Recency distribution and conversion window
The recency factor affects the CVR (left)
Campaign 1 sets a long recency cap -> waste of budget
Campaign 2 sets a short recency cap -> poor performance
The wide conversion window (right)
challenges attribution models
30

31. Periodic patterns contd.
The winning bids peak at 8-10am due to intensive competition
31

32. Change of winner
Level of competition
(number of bidders)
The more bidders, the higher chance of winner change,
which makes it harder to detect a dynamic reserve price
32

33. Bids’ distribution
Accepted (p>0.05)
Rejected
AD test per auction
0.343
0.657
AD test per placement
0.000
1.000
CQ test per auction
0.068
0.932
The commonly adopted assumption of Uniform distribution or Log-normal distribution
were mostly rejected
• Anderson-Darling test for Normality
• Chi-squared test for Uniformity
Finding the best fit of bids’ distribution is important:
• Optimal reserve price
• Bid landscape forecasting
• etc.
And what’s the granularity? (placement, geographical location, time & weekday, etc.)
33

34. Budgeting and daily pacing
Real Time Bid Optimization with Smooth Budget Delivery in Online Advertising, KC Lee et al., 2013
34

35. Budgeting and daily pacing
35

36. A mixture of 1st and 2nd price auctions
• A high soft floor price can
make it 1st price auction
(In RTB, floor prices are not always
disclosed before auctions)
• In our dataset, 45% 1st price
auctions consumed 55%
budgets
• The complicated setting puts
advertisers in an unfavourable
position and could damage the
ad eco-system
36

37. Overview: references
•
•
•
•
•
•
The History of Advertising: How Consumers Won the War for Their Attention, HubSpot, 2013
blog.hubspot.com/the-history-of-advertising-war-for-consumer-attention-slideshare
How Cluttered Is the Advertising Landscape, Really? HubSpot, 2013
blog.hubspot.com/how-cluttered-is-advertising-landscape-timeline
Navigating Planet Ad Tech, MIT Technology Review, 2013
www.technologyreview.com/view/518551/the-evolution-of-ad-tech/
Internet Advertising: An Interplay among Advertisers, Online Publishers, Ad Exchanges and Web Users, S Yuan
et al., 2013
arxiv.org/abs/1206.1754
Ad exchanges: research issues, S Muthukrishnan, 2009
sites.google.com/site/algoresearch/start2.pdf
Behind the banner (A visualization of the adtech ecosystem), Adobe, 2013
cmsummit.com/behindthebanner/
37

38. Part 3: Demand side optimisation
• Bid optimisation
• Conversion attribution
38

39. Bid optimisation
• Input
– logs for auctions, impressions and
events
– targeting rules
– budgets and pacing preference
– internal/external user data
• The Decision Engine
– Gradient Boosting Regression
decision Tree, etc.
– fast & scalable
• Output
– to bid or not
– how much
39

40. Bid optimisation
• Baseline (constant or random, for exploration)
• Simple rule based (to bid high if the return is high)
– bid = base * pred_CTR / avg_CTR
– bid = conv_value * CVR * ROI
• Regression for estimation
– Generalised linear regression models (logistic, Bayesian probit, FTRL-Proximal,
etc.)
– Tree based models (random forest, gradient boosting regression tree, etc.)
– Neural networks and deep learning
40

41. Bid optimisation
• Looks good, but…
– metrics for evaluation?
– exploration vs.. exploitation (esp. for cold-start campaigns)
– risks (variance or confidence intervals from estimation)
– practical constraints (branding, overspending risks, inconsistent billing units, etc.)
• E-E problem
– Interactive collaborative filtering
– dimension deduction, correlation, etc.
• Risks
– Defining the Utility as the objective
– Portfolio theory
41

42. Metrics
• Top funnel metrics (to gain brand awareness)
– brand recall (awareness uplift)
– branded search
– direct website traffic
• Mid funnel metrics (to educate and engage the prospects)
– cost per new website visitor
– page view & form uplift
• Bottom funnel metrics (to generate value both online and offline)
– total conversion
– cost per conversion
– opportunity contribution (interested but not converted yet)
– revenue
courtesy of Adexchange
42

43. Transfer learning
• The Problem
– CTR is no good metrics but CVR is
too low
• Task
– To train on site visits
• Challenge
– Which site visits, and weight?
– Data availability
• Solution
– Similarity (contextual as a priori,
Bayesian)
Evaluating and Optimizing Online Advertising: Forget the Click, But There are Good Proxies, B Dalessandro, 2012
43

44. Conversion attribution problem
Dr Samuel Seljan from AppNexus
44

45. AppNexus
• AppNexus – Open and customizable advertising technology platform
•
Process over 50 Billion ad requests per day
•
Allow buyers to buy from over 90% of the web, including Facebook
•
Clients are advertisers, ad agencies, content providers, and ad networks
•
Major clients include:
• Microsoft
• Netflix
• eBay
• Zynga
• Interactive Media
• Orange - European telecom/media conglomerate
•
WPP - world’s second largest ad agency
45

46. Why advertise?
“Done well, advertising sends a whisper to your
impulses – a primal wind at the back of your neck,
suggesting where to go and what to do.”
-Don Draper
46

47. Fundamental question of advertising
• But, does advertising work?
•
Which ads work with what audience?
• Do the benefits of advertising outweigh it’s costs?
– Incremental revenue > Marginal cost?
47

48. Fundamental question of advertising
• The promise of digital advertising: precise measurement of users’ responses
to ads
• 1990s: Click tracking
• Compare CTRs across many, many dimensions:
• Campaign, image, time of day, region, location on page, gender, etc.
• Limitations?
48

49. Fundamental question of advertising
• The promise of digital advertising: precise measurement of users’ responses
to ads
• 1990s: Click tracking
• Compare CTRs across many, many dimensions:
• Campaign, image, time of day, region, location on page, etc
• Limitations?
• Late 2000s: Conversion tracking
• Conversion: when a user sees and ad and then takes an action, e.g. buys a pair or shoes
• Cost Per Action (CPA) payment: advertisers only pay when a conversion occurs
• Traders (agents of buyers) or sellers take on all the risk
• Does this answer the fundamental question of advertising?
49

50. Problems with CPA advertising
1.
Users often see many ads for the same brand on many sites
2.
Only includes online actions
3.
Causal inference – what does the association between seeing an ad and
converting mean?
4.
Ration of conversions per ads is often very small
–
Between 1-5 conversions per 100,000 impressions is common
–
Thus, takes many ads to learn “true” conversion rate.
•
For a one month campaign with a $5,000 budget, possible to learn conversion rate with
5% error on roughly 10 different web sites!
–
Difference between 1 and 5 conversions per 100,000 impression is difference
between a profitable and unprofitable campaign
50

51. Problems with CPA advertising
1.
Users often see many ads for the same brand on many sites
•
Which ad “is responsible” for the conversion?
•
Industry standard is “last touch” attribution
–
–
•
Previous graph is misleading!
Doesn’t show how many times a user saw ad
Connection to frequency optimization: creates a bias towards higher frequency ads
–
Last touch is the most recent ad, but we don’t know for sure that user even saw the
most recent ad – we just have a record of it
–
If effect of seeing ad is cumulative, this under weights importance of first view
51

52. Problems with CPA advertising
1.
–
2.
–
•
Users often see many ads for same brand on many sides
Which ad and site gets credit for the conversion?
No tracking of offline purchases
Technological and privacy challenges
3. The fundamental problem of causal inference
(Ad tech version)
Incremental revenue from ad j for user i =
Lifetime revenuei | i sees j– Lifetime revenuei | i does not see j
– But, each user either sees or does not see an ad so this cannot be calculated, even with
limitless data!
– Moreover, advertisers target users that are more likely to buy! (retargeting), thus lifetime
revenuei | i sees j is very likely to overestimate incremental revenue.
•
Most CPA optimization creates selection bias

53. Problems with CPA advertising
• Alternative framing: most CPA buying algorithms are predicting who is most
likely to buy and then focusing (targeting) buying on these users
• Thus, advertisers may see a lot of conversions associated with ads on some sites
on some users, but do not know how much revenue they would have had without
those ads
• Example: amazon targets ads at people who have recently searched for an item
on their website.
• These people are more likely to buy on Amazon than those who have not recently
searched
• But, they are also more likely to buy without seeing an ad

54. Problems with CPA advertising
•
Problem is more important for some brands than others
• For internet advertising, the potential scale of the problem can be considered by
thinking about:
Lifetime revenuei | i does not see digital ad
• For what types of campaigns is this likely to be a big problem? A small problem?
•
Principal agent problem: the people that need to understand this are the
brands themselves
• Agents buying for brands, do not have a short term incentive to solve problem
– they get paid per conversion!
• Selling more rigorous CPA optimization to brands is challenging
54

55. Solutions to problems with CPA advertising

56. Problem 1: Many ads per conversion
• AppNexus Solution 1: custom conversion attribution
• We track conversions, but allow clients to divide conversion among ads
using their own “secret sauce”
• AppNexus Solution 2: Conversion Funnel
• Use events higher up the funnel to predict final sale
56

57. Problem 2: Offline tracking
• AppNexus Solution 1: allow for integrations with offline data providers and
the insertion of external data into optimization
• Other solutions?
• A privacy quid pro quo? Data for savings?
57

58. Problem 3: Fundament Problem of Causal Inf.
• AppNexus Solution: Random assignment
• Randomly assign users to group A (sees ad) or B (doesn’t see ad)
• Estimate incremental revenue from ad as:
conversion value * p(Conversion |A ) – p(Conversion | B)
– limitations: scalability, does not include off-line revenue or model social returns
• This is a problem for both group A and group B for larger brands
58

59. Problem 3: Fundament Problem of Causal Inf.
• Gold standard:
• Fowler et al. (2012): Facebook “I voted” and turnout
– RA to three groups:
» 1. Top panel
» 2. Second panel
» 3. No message
• Used federal data to compare turnout rates in groups & friends of those in each gorup
– .4% higher turnout of second gorup
• Combines solutions 2 and 3 (randomization addresses problems 2 and 3!)
59

60. Problem 3: Fundament Problem of Causal Inf.
• Remaining questions for RA: how to combine RA with other elements of a
CPA optimization algorithm…
– Over how many groups should one randomize?
» E.g. it could solve the frequency – conversion attribution problem, but that’s
a lot of groups
– What percent of impressions should be in test and control group?
60

61. Demand side optimisation: references
•
Optimal bidding on keyword auctions, B Kitts and B Leblanc, 2004
•
Stochastic gradient boosted distributed decision trees, J Ye et al., 2009
•
Web-scale bayesian click-through rate prediction for sponsored search advertising in Microsoft's Bing search
engine, T Graepel et al., 2010
•
Web-search ranking with initialized gradient boosted regression trees, A Mohan et al., 2011
•
A Gentle introduction to random forests, ensembles, and performance metrics in a commercial system, D
Benyamin, 2012
citizennet.com/blog/2012/11/10/random-forests-ensembles-and-performance-metrics/
•
A 61-million-person experiment in social influence and political mobilization, RM Bond et al., 2012
•
Deep metworks for predicting ad click through rates, G Corrado, 2012
•
Click modeling for display advertising, O Chapelle, 2012
•
Causal reasoning and learning systems, L Bottou and E Portugaly, 2012
•
Ad click prediction: a view from the trenches, HB McMahan et al., 2013
•
Deep learning, yesterday, today, and tomorrow, K Yu et al., 2013
•
Deep learning of representations: looking forward, Y Bengio, 2013
61

62. iPinyou global bidding algorithm competition
Dr Xuehua Shen from iPinyou
62

63. Best Algorithm

64. Maximize #clicks + N * #conversions
Subject to the fixed budget

65. 3 Milestones +
1,000,000
Grand Prize

66. iPinYou Contest vs. Netflix Prize
Open Question
Offline & Online Evaluation
Production setting
Meaningful metrics
Dynamic data set
Short time span

71. 7.5G
bid:
imp:
clk:
conv:
13.6M
9.2M
7.5K
72

72. Dropbox:
https://www.dropbox.com/sh/xolf5thu8jsb
mfu/kBrAsSxtAN
百度网盘:
http://pan.baidu.com/share/link?shareid=
374646&uk=3037373637

73. April 20 May 3
May 16

74. 2000+
submissions

78. ml_rush, the9thbit, newline
05.16 ~ 05.22 Warmup
05.23 ~ 05.25 Bidding

81. Not just CTR

83. June 1 ~ August 31
Sept 1 ~ Sept 30
Sept 6 ~ Sept 12
Sept 13 ~ Sept 15
Offline
Online
Warmup
Bidding

85. Season 2 vs. Season 1
Support Python, R, Java
Competition platform
Top 5 go to Online stage
More bonus
Team membership (6 to 10)

87. 2x Data
User Profile

88. July 5
July 12
Aug 31
Aug 31’

91. 4000+
submissions

92. Bidathon 2

93. Rank
Team
name
#Bid
1
o_o
50,874,976 4,658,979 4,265 4
1497.55 9.2%
0.092% 4289
2
梦想照进
79,426,606 7,196,004 4,061 1
现实
1481.59 9.1%
0.056% 4067
3
UCL-CA
3,597,284
2,059,509 1,989 1
1500.01 57.3% 0.097% 1995
4
Again
21,099,070 3,503,178 1,397 2
1499.99 16.6% 0.040% 1409
5
deep_ml
4,682,521
1500.08 40.3% 0.061% 1148
#Imp
#Clk
#Co Spendin Win
n
g
Rate
1,886,929 1,142 1
CTR
Final
Score

94. Bid More, Bid
Less

98. Season 3
Oct 1 ~ Nov 15
Nov 15 ~ Dec 15
Offline
Online

99. Season 3 vs. Season 1/2
Even bigger data set
Focus on Online Stage
Mobile Campaign

102. Any question sent to
dsp-competition@ipinyou.com
320076711
全球RTB算法大赛
iPinYou Global RTB Bidding
Algorithm Competition

103. Part 4: Supply side optimisation
• Typical revenue models
• Ad density optimal control
• Reserve price optimisation
• Ad channel selection
• Connecting the supply side markets
• Data leakage protection and pricing
103

104. Typical revenue models for the supply side
• Subscription access to content (FT.com)
• Pay Per View access to document (Downloading a paper outside the campus)
• CPM display advertising on site
• CPC advertising on site (Google AdSense)
• Sponsorship of site sections or content types (typically fixed fee for a period)
• Affiliate revenue (Compare shopping, CPA/CPC)
• Subscriber data access for marketing (VISA & MasterCard)
• User contributed data for marketing (Surveys)
Publishers will seek to use the best combination of these techniques
104

105. Ad density
The task:
•
To find the optimal advertising
density (number of ad placements)
for a given website
The challenges:
•
Users’ preference model
•
Expected CPM
•
Competition
The assumption:
• Using real-time bidding only
105

106. No ads
Some websites do not rely on
ads to compensate the
maintenance cost
• Government
• Education
• Most of .org
courtesy of www.gov.uk
106

107. All ads
• Created by Alex Tew in
2005
• Selling 100k 100-pixels
at $100 each
• Sold out in 4 months
• Almost 0% CTR
courtesy of www.milliondollarhomepage.com
107

108. Ad density: example
Apr 2010
Sep 2013
courtesy of archive.web.org
108

109. Ad density: example
Question: is it reasonable to put on so many more ads?
courtesy of Quantcast
109

110. Ad density: an optimal control problem
• Assumptions
– Ad density and impressions determine revenue
Ad density
CPM
Impressions (page views) Maintenance cost factor
– Ad density determines impressions
Content attraction Ad repellence
Natural growth
Question: what’s the optimal densities of multiple publishers under competition?
Management and valuation of advertisement-supported web sites, Dewan et al. 2005
110

111. Reference: ad density, layout & pricing
•
Management and valuation of advertisement-supported web sites, RM Dewan, 2003
•
Optimal pricing and advertising policies for web services, S Kumar et al., 2004
•
Is revamping your web site worthwhile? EY Huang, 2005
•
An economic analysis of ad-supported software, BJ Jiang, 2007
•
Dynamic pricing and advertising for web content providers, S Kumar and SP Sethi, 2009
•
Pricing display ads and contextual ads: Competition, acquisition, and investment, YM Li and JH Jhang-Li, 2009
•
Dynamic ad layout revenue optimization for display advertising, H Cheng et al., 2012
•
Automatic ad format selection via contextual bandits, L Tang et al., 2013
111

112. Reserve price optimisation
The task:
•
To find the optimal reserve
prices
The challenge:
•
Practical constraints v.s
common assumptions (bids’
distribution, bidding private
values, etc.)
The assumptions:
Even in the 2nd price auction,
the winner does not always
pay the 2nd highest bid (or
minimal + $0.01)
•
2nd price auction
•
With only hard floor price
112

113. Reserve price: flowchart
Suppose it is 2nd price auction
• Normal case: b2 > a
• Preferable case: b1 > a > b2
• Undesirable case: a > b1
113

114. Reserve price: example
• 2 bidders, Uniform[0, 1]
• Without a reserve price
• With the optimal auction theory
Reserve prices in internet advertising auctions: A field experiment, Ostrovsky and Schwarz, 2011
114

115. Reserve price: the optimal auction theory
• In the 2nd price auctions, advertisers bid their private values [𝑏1 , … , 𝑏 𝐾 ]
• Values are independently distributed and drawn from certain distributions
– Uniform
𝐹 𝒃 = 𝐹1 𝑏1 × ⋯ × 𝐹 𝐾 (𝑏 𝐾 )
– Log-normal
• The publisher also has a private value 𝑉𝑝
• The optimal reserve price is given by
𝛼−
1− 𝐹 𝒃
− 𝑉𝑝 = 0
′ 𝒃
𝐹
Questions:
• Are advertisers bidding their private values?
• Does Uniform/Log-normal fit well?
Optimal Reservation Prices in Auctions, Levin and Smith, 1996
115

116. Reserve price: field experiment results
Reserve prices in internet advertising auctions: A field experiment, Ostrovsky and Schwarz, 2011
116

117. Reserve price: field experiment results
Reserve prices in internet advertising auctions: A field experiment, Ostrovsky and Schwarz, 2011
117

118. Reserve price: detection and reaction
• A dynamic and repeated game between the winner (w) and the publisher (p)
• Extension form representation
– Information nodes:
• 𝐼1 : the winning bid 𝑏1 is higher
• 𝐼2 : the reserve price 𝛼 is higher
– Actions:
•
•
•
•
𝑎 𝑤1 : to increase
𝑎 𝑤2 : to increase
𝑎 𝑤3 : to decrease
𝑎 𝑤4 : to decrease
𝑏1 so that
𝑏1 so that
𝑏1 so that
𝑏1 so that
𝑏1 ≥
𝑏1 <
𝑏1 ≥
𝑏1 <
𝛼
𝛼
𝛼
𝛼
• 𝑎 𝑝1 : to increase 𝛼 so that 𝛼 ≥ 𝑏1
• 𝑎 𝑝2 : to increase 𝛼 so that 𝛼 < 𝑏1
• 𝑎 𝑝3 : to decrease 𝛼 so that 𝛼 ≥ 𝑏1
• 𝑎 𝑝4 : to decrease 𝛼 so that 𝛼 < 𝑏1
118

119. Reserve price: detection and reaction
payoff of the winner and the publisher
The dynamic and static game tree for the auction with reserve price
119

120. Reserve price: detection and reaction
• Consider playing the game repeatedly
– If the reserve price was higher, should the publisher lower it?
– The optimal auction theory
• Advertisers want to learn the publisher’s private value distribution, too
– What is the absolute minimal price that can be accepted?
• Questions
– What are the best response functions for both players?
– What are the dominant strategies and equilibrium?
120

121. Reserve price: references
•
On optimal reservation prices in auctions, Engelbrecht-Wiggans, 1987
•
Optimal reservation prices in auctions, Levin and Smith, 1996
•
Auction theory: a guide to the literature, Klemperer, 1999
•
Reserve prices in internet advertising auctions: a field experiment, Ostrovsky and Schwarz, 2009
•
Auction theory 2nd edition, Krishna, 2009
•
Optimal reserve price for the generalized second-price auction in sponsored search advertising, Xiao et al.,
2009
•
Optimal auction design and equilibrium selection in sponsored search auctions, Edelman and Schwarz, 2010
•
Optimal auction design in two-sided markets, R Gomes, 2011
121

122. Ad channel selection
• The task:
– There are multiple ad
channels giving
different payoffs over
time. Which one to
use?
• The challenge:
– Too many possible
candidates
– The payoffs change
over time
Sequential Selection of Correlated Ads by POMDPs, Yuan and Wang, 2012
122

123. Ad channel selection contd.
• A sequential selection problem
• Value iteration exact solution (high computational complexity)
• Multi-armed bandit approximation
Sequential Selection of Correlated Ads by POMDPs, Yuan and Wang, 2012
123

124. Sequential selection: references
•
Dynamic programming, RE Bellman, 1957
•
Multi-armed bandits and the Gittins index, P Whittle, 1980
•
A survey of POMDP applications, AR Cassandra, 1998
•
A survey of POMDP solution techniques, KP Murphy, 2000
•
Finite-time analysis of the multi-armed bandit problem, P Auer, P. et al.,2002
•
Multi-armed bandit algorithms and empirical evaluation, J Vermorel and M Mohri, 2005
124

125. Impression allocation between GD and NGD
• Sometimes, ad channels could have different attributes:
– GD: Guaranteed Delivery (contracts)
– NGD: Non-Guaranteed Delivery (auctions)
• Given a time window, the publisher decides
– To accept or reject a contract proposal
– To allocate impressions among multiple contracts and auctions
(NGD can be modelled as an already accepted contract with ∞ required
impressions and 0 under-delivery penalty)
Dynamic Revenue Management for Online Display Advertising, Roels and Fridgeirsdottir, 2008
125

126. Connecting GD and NGD
Four (4) major types of inventories in Programmatic selling
Now they are priced differently and separately
Separated markets implies inefficiency and arbitrage
courtesy of Internet advertising bureau
126

127. Automated (programmatic) guaranteed delivery
• AOL Upfront
– Will take effect January 1, 2014
– Two brands and five agencies have committed, around $10m for each agency
(undisclosed)
– AOL’s ad placements, e.g. The Huffington Post, TechCrunch and StyleList
– A private marketplace in the beginning
• Question
– Selling mechanisms (auction, queue, etc.)
– Inventory allocation and reserve prices
courtesy of AOL
127

128. Optimal pricing of a guaranteed delivery contract
• Suppose the publisher wants to sell 𝑆 impressions from time step 𝑇 + 1
– In advance: guaranteed delivery contracts
– On spot: RTB auctions (non-guaranteed, 2nd price auction)
• Consider the total demand as 𝑄
• The private value distribution of an advertiser is 𝐹 ⋅
• The utility of an advertiser is 𝑈 𝑎 ⋅ = 𝐹 ⋅ + 𝑔 𝑡
– Willing to pay higher if could buy in advance
What is the optimal price
at 0 < 𝑡 < 𝑇 + 1 ?
• The utility of the publisher is 𝑈 𝑝 ⋅ = 𝑅 ⋅ + ℎ(𝑡)
– Willing to charge lower if could sell in advance
128

129. Guaranteed delivery: references
•
Optimal dynamic auctions for display advertising, YJ Chen, 2009
•
Pricing guaranteed contracts in online display advertising, V Bharadwaj, 2010
•
Risk-aware revenue maximization in display advertising, A Radovanovic and WD Heavlin, 2012
•
Optimal allocation for display advertising, H Rui et al., 2012
•
A unified optimization framework for auction and guaranteed delivery in online advertising, K Salomatin,
2012
•
Maximally representative allocations for guaranteed delivery advertising campaigns, RP McAfee, 2013
129

130. Bid landscape forecasting
The tool usually exists as a service provided to advertisers
courtesy of Google AdWords
130

131. Bid landscape forecasting
• The task:
Given a campaign (a set of
targeting rules), what is the
bid-impression distribution
for a given venue (domain,
placement, etc.)?
• The challenge:
Forecasting for new &
changed campaigns
Forecasting the win rate for
unseen bids
Bid landscape forecasting in online ad exchange marketplace, Y Cui et al,. 2011
131

132. Bid landscape forecasting
A Generative Model based ad Impression Forecasting method
Ad impression forecasting for sponsored search, A Nath et al., 2013
132

133. Bid landscape forecasting: references
•
Bid landscape forecasting in online ad exchange marketplace, Y Cui et al., 2011
•
Handling forecast errors while bidding for display advertising, KJ Lang et al., 2012
•
Ad impression forecasting for sponsored search, A Nath et al., 2013
•
Forecasting user visits for online display advertising, S Cetintas et al., 2013
•
Predicting advertiser bidding behaviors in sponsored search by rationality modeling, H Xu et al., 2013
•
Optimizing volume and frequency forecasts for an online video advertiser, J Talbot et al., 2013
133

134. Data leakage protection
• Every player in the ad eco-system realises the value of audience data
– who owns it?
– what’s its value?
• The data leakage problem
– buyers collect user data from premium website
– then retarget these users on cheap inventories
• The task
– To learn who is collecting user data on the webpage (piggybacks)
– To stop the unauthorized collection and ask for payment
• The challenge
– The optimal price: limiting the user data access will hurt the CPM
134

135. Part 5: Financial methods in Computational Advertising
• Game theory basics
• Ad options
135

136. Examples
Auction for sharing compute resources
Financial methods and game theory have a long history in CS research
A futures market in computer time, IE Sutherland, 1968
136

137. Examples contd.
Auction and futures in cloud computing
• Amazon EC2 is a web service that provides resizable compute capacity in the cloud
• In late 2009, Amazon announce its spot instances pricing system
Deconstructing Amazon EC2 Spot Instance Pricing, OA Ben-Yehuda, 2011
137

138. Examples contd.
In the age of the Internet, fixed prices are a thing of the past
Professor Oren Etzioni
courtesy of Wall Street Journal
138

139. Game theory basics
• A game is “a competitive activity … in which players contend with each other
according to a set of rules”
• A strategic game (with ordinal preferences) consists of
– a set of players
– for each player, a set of actions
– for each player, preferences over the set of action profiles
• The best response
• The Nash equilibrium of static games
An introduction to game theory, MJ Osborne, 2003
139

140. Example: the prisoner's dilemma
• A typical example of noncooperative game
• The strictly dominant strategy
for both players is to confess,
which also forms the Nash
equilibrium of the game
• When played iteratively, the
winning deterministic strategy is
tit-for-tat
(first cooperate, then subsequently
replicate an opponent's previous
action)
The mysterious benedict society and the prisoner’s dilemma, TL Stewart, 2009
courtesy of Encyclopaedia Britannica, 2006
140

141. Example: The game of chicken
• While each player prefers not to
yield to the other, the worst possible
outcome occurs when both players
do not yield.
– The nuclear crisis
Dare
Chicken
– The promise on advertising effects
0, 0
7, 2
– The bidding on similar audiences
Chicken 2, 7
6, 6
Dare
courtesy of Rebel Without a Cause
simultaneously
141

142. Example: The Cournot competition
• Assumptions
– There is more than one firm and all firms produce a
homogeneous product, i.e. there is no product
differentiation;
– Firms do not cooperate, i.e. there is no collusion;
– Firms have market power, i.e. each firm's output decision
affects the good's price;
– The number of firms is fixed;
– Firms compete in quantities, and choose quantities
simultaneously;
– The firms are economically rational and act strategically,
usually seeking to maximize profit given their competitors'
decisions.
courtesy of palimpsestes.fr
142

143. Example: The Cournot competition
•
𝑝1 , 𝑝2 : prices
•
𝑞1 , 𝑞2 : quantities
• Firm 1’s profit:
Π1 = 𝑞1 𝑃 𝑞1 + 𝑞2 − 𝑐
• Firm 1’s best response function:
𝜕Π1
𝑅(𝑞2 ) =
𝜕𝑞2
• To obtain the equilibrium:
𝑅 𝑞2 = 𝑅 𝑞1
(the intersection)
courtesy of Wikipedia
143

144. Example: The Bertrand competition
• Assumptions
– Firms compete by setting prices simultaneously and
consumers want to buy everything from a firm with a
lower price
– If two firms charge the same price, consumers
demand is split evenly between them
courtesy of Wikipedia
144

145. Example: The Bertrand competition
• If both firms set equal prices
above marginal cost, firms
would get half the market at a
higher than MC price
• By lowering prices just slightly,
both firms are
pricing at
marginal cost
a firm could gain the whole
market
• Both firms are tempted to
lower prices as much as they
can
• It would be irrational to price
below marginal cost, because
courtesy of Wikipedia
the firm would make a loss
145

146. Application of the duopoly competition
• If capacity and output can be easily changed -> Bertrand model
• if output and capacity are difficult to adjust -> Cournot model
• Analogy
– Two publishers serving similar content
– Premium and long-tail publishers seeing similar users
– etc.
146

147. References: financial methods and game theory basics
•
A policy framework for trading configurable goods and services in open electronic markets, S Lamparter, 2006
•
Planning and pricing of service mashups, B Blau et al., 2008
•
Web service derivatives, T Meinl and B Blau, 2009
•
How to coordinate value generation in service networks, B Blau et al., 2009
•
Enabling cloud service reservation with derivatives and yield management, T Meinl et al., 2010
•
Web services advanced reservation contracts, C Weinhardt et al., 2011
•
Finite automata play the repeated prisioners dilemma, A Rubinstein, 1986
•
A course in game theory, MJ Osborne and A Rubinstein, 1994
•
An introduction to game theory, MJ Osborne, 2004
•
Sponsored search auctions: an overview of research with emphasis on game theoretic aspects, P Mailléet al.,
2012
•
Repeated keyword auctions played by finite automata, W Ding et al, 2013
147

148. Ad options
• The task:
– To sell impressions in advance
(a natural extension to the programmatic
guarantee)
– Both party can choose to exercise or not
• The (pricing) challenge:
– Impression prices are volatile
– Non-storability: impressions cannot be
bought and kept
– Not just about the price movements: the
uncertainty of traffic volume, CTR and etc.
courtesy of Webscope from Yahoo! Labs
148

149. Ad options contd.
Advertisers
 secure impressions delivery
 reduce uncertainty in auctions
 cap cost
Publishers
 sell the inventory in advance
 have a more stable and predictable
revenue over a long-term period
 increase advertisers’ loyalty
Benefits
149

150. Ad options contd.
t=T
Pays £ upfront option
5
price to obtain the
option.
t=0
Sells a list of ad keywords via a multikeyword multi-click option
multi-keyword multi-click option (3 month
term)
upfront
fee
(m = 100)
Submits a request of
guaranteed ad delivery
for the keywords ‘MSc
Web Science’, ‘MSc Big
Data Analytics’ and ‘Data
Mining’ for the future 3
month term [0, T], where
T = 0.25.
fixed CPCs
‘MSc Web Science’
£
1.80
‘MSc Big Data
Analytics’
£
6.25
‘Data Mining’
£
5
keywords list
£
8.67
Timeline
online advertiser
search engine
Multi-Keyword Multi-Click Advertisement Option Contract for Sponsored Search, B Chen et al., 2013
150

151. Exercising the option
Pays £
1.80 to the search
engine for each click until
the requested 100 clicks
are fully clicked by
Internet users.
Exercises 100 clicks of
‘MSc Web Science’ via
option.
t=T
t = t1c
Reserves an ad slot of the keyword ‘MSc
Web Science’ for the advertiser for 100
clicks until all the 100 clicks are fully
clicked by Internet users..
t = t1
t=0
Timeline
online advertiser
search engine
Multi-Keyword Multi-Click Advertisement Option Contract for Sponsored Search, B Chen et al., 2013
151

152. Not exercising the option
Pays the GSP-based CPC
for each click if winning
the bid.
If the advertiser thinks
the fixed CPC £
8.67 of the
keyword ‘Data Mining’ is
expensive, he/she can
attend keyword auctions
to bid for the keyword as
other bidders, say £
8.
t=T
Selects the winning bidder for the
keyword ‘Data Mining’ according to the
GSP-based auction model.
t =…
t=0
Timeline
online advertiser
search engine
Multi-Keyword Multi-Click Advertisement Option Contract for Sponsored Search, B Chen et al., 2013
152

153. Ad options pricing
• Building blocks
– No-arbitrage [F Black and M Scholes1973; H Varian1994]
– Stochastic underlying keyword CPC [P Samuelson1965]
– Terminal value formulation
• Formula
– n=1, Black-Scholes-Merton European call
– n=2, Peter Zhang dual strike European call
– n>=3, Monte Carlo method
Multi-Keyword Multi-Click Advertisement Option Contract for Sponsored Search, B Chen et al., 2013
153

154. Ad options: references
•
Option pricing: a simplified approach, J Cox et al., 1979
•
Online ad slotting with cancellations, F Constantin, 2008
•
A truthful mechanism for offline ad slot scheduling, J Feldman et al., 2008
•
Selling ad campaigns: online algorithms with cancellations, M Babaioff et al., 2009
•
Options, futures and other derivative securities (7th edition), J Hull, 2009
•
Online advertisement service pricing and an option contract, Y Moon and CY Kwon, 2010
•
Selling futures online advertising slots via option contracts, J Wang and B Chen, 2012
•
Multi-keyword multi-click advertisement option contract for sponsored search, B Chen et al., 2013
154

155. Additional references
•
Internet advertising and the generalized second price auction: selling billions of dollars worth of keywords, B
Edelman, 2005
•
Price cycles in online advertising auctions, X Zhang and J Feng, 2005
•
Budget optimization in search-based advertising auctions, J Feldman et al., 2007
•
The economics of the online advertising industry, DS Evans, 2008
•
Expressive banner ad auctions and model-based online optimization for clearing, C Boutilier et al., 2008
•
Computational advertising, AZ Broder, 2008
•
Algorithmic methods for sponsored search advertising, J Feldman and S Muthukrishnan, 2008
•
Internet ad auctions: Insights and directions, S Muthukrishnan, 2008
•
The online advertising industry: economics, evolution, and privacy, , DS Evans, 2009
•
Ad exchanges: Research issues, S Muthukrishnan, 2009
•
Adaptive bidding for display advertising, A Ghosh et al., 2009
•
The arrival of real-time bidding, Google, 2011
•
Algorithms and strategies for web advertising, P Papadimitriou, 2011
•
OpenRTB API specification, IAB, 2012
155

156. Additional references
•
Targeted, not tracked: client-side profiles and privacy-friendly behavioral advertising, M Bilenko and M
Richardson, 2012
•
Computational advertising in social networks, A Bhasin, 2012
•
Size, labels, and privacy in targeted display advertising, C Perlich, 2012
•
Estimating conversion rate in display advertising from past erformance data, K Lee et al,. 2012
•
Handling forecast errors while bidding for display advertising, KJ Lang et al., 2012
•
Marketing campaign evaluation in targeted display advertising, J Barajas et al., 2012
•
Ad exchange-proposal for a new trading agent competition game, M Schain and Y Mansour, 2012
•
Auctions for online display advertising exchanges: approximations and design, S Balseiro et al., 2012
•
Real-time bidding for online advertising: measurement and analysis, S Yuan et al., 2013
•
Impression fraud in on-line advertising via pay-per-view networks, K Springborn and P Barford, 2013
•
An overview of computational challenges in online advertising, RE Chatwin, 2013
•
Competition and yield optimization in ad exchanges, SR Balseiro, 2013
•
Internet advertising revenue report, IAB and PwC
156