Internet advertising auctions
Download
1 / 146

Internet Advertising Auctions - PowerPoint PPT Presentation


  • 439 Views
  • Updated On :

Internet Advertising Auctions. David Pennock , Yahoo! Research - New York Contributed slides: K.Asdemir, H.Bhargava, J.Feng, S.Lahaie , M.Schwarz. Advertising Then and Now. Then: Think real estate Phone calls Manual negotiation “Half doesn’t work”.

loader
I am the owner, or an agent authorized to act on behalf of the owner, of the copyrighted work described.
capcha
Download Presentation

PowerPoint Slideshow about 'Internet Advertising Auctions' - Jeffrey


An Image/Link below is provided (as is) to download presentation

Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author.While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server.


- - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - -
Presentation Transcript
Internet advertising auctions l.jpg

Internet Advertising Auctions

David Pennock, Yahoo! Research - New York

Contributed slides:K.Asdemir, H.Bhargava, J.Feng, S.Lahaie, M.Schwarz


Advertising then and now l.jpg
Advertising Then and Now

  • Then: Think real estatePhone callsManual negotiation“Half doesn’t work”

  • Now: Think Wall StreetAutomation, automation, automationAdvertisers buy contextual attention: User i on page j at time tComputer learns what ad is bestComputer mediates ad sales: Auction!Computer measures which ads work


Advertising then now video l.jpg
Advertising Then & Now: Video

http://ycorpblog.com/2008/04/06/this-one-goes-to-11/


Advertising now tools disciplines l.jpg

Auctions

Machine learning

Optimization

Sales

Economics &Computer Science

Statistics &Computer Science

Operations Research Computer Science

Marketing

Advertising: NowTools Disciplines


Sponsored search auctions l.jpg

search “las vegas travel”, Yahoo!

“las vegas travel” auction

Sponsored search auctions

Space next to search results is sold at auction



Outline l.jpg
Outline

  • Motivation: Industry facts & figures

  • Introduction to sponsored search

    • Brief and biased history

    • Allocation and pricing: Google vs old Yahoo!

    • Incentives and equilibrium

  • Ad exchanges

  • Selected survey of research

  • Prediction markets


Auctions applications l.jpg

eBay

216 million/month

Google / Yahoo!

11 billion/month (US)

Auctions Applications


Auctions applications9 l.jpg

eBay

Google

Auctions Applications


Auctions applications10 l.jpg

eBay

Google

Auctions Applications


Newsweek june 17 2002 the united states of ebay l.jpg
Newsweek June 17, 2002“The United States of EBAY”

  • In 2001: 170 million transactions worth $9.3 billion in 18,000 categories “that together cover virtually the entire universe of human artifacts—Ferraris, Plymouths and Yugos; desk, floor, wall and ceiling lamps; 11 different varieties of pockets watches; contemporary Barbies, vintage Barbies, and replica Barbies.”

  • “Since everything that transpires on Ebay is recorded, and most of it is public, the site constitutes a gold mine of data on American tastes and preoccupations.”


The united states of search l.jpg
“The United States of Search”

  • 11 billion searches/month

  • 50% of web users search every day

  • 13% of traffic to commercial sites

  • 40% of product searches

  • $8.7 billion 2007 US ad revenue (41% of $21.2 billion US online ads; 2% of all US ads)

  • Still ~20% annual growth after years of nearly doubling

  • Search data: Covers nearly everything that people think about: intensions, desires, diversions, interests, buying habits, ...


Online ad industry revenue l.jpg
Online ad industry revenue

http://www.iab.net/media/file/IAB_PwC_2007_full_year.pdf


Introduction to sponsored search l.jpg

Introduction tosponsored search

What is it?

Brief and biased history

Allocation and pricing: Google vs Yahoo!

Incentives and equilibrium


Sponsored search auctions15 l.jpg

search “las vegas travel”, Yahoo!

“las vegas travel” auction

Sponsored search auctions

Space next to search results is sold at auction


Sponsored search auctions16 l.jpg
Sponsored search auctions

  • Search engines auction off space next to search results, e.g. “digital camera”

  • Higher bidders get higher placement on screen

  • Advertisers pay per click: Only pay when users click through to their site; don’t pay for uncliked view (“impression”)


Sponsored search auctions17 l.jpg
Sponsored search auctions

  • Sponsored search auctions are dynamic and continuous: In principle a new “auction” clears for each new search query

  • Prices can change minute to minute;React to external effects, cyclical & non-cyc

    • “flowers” before Valentines Day

    • Fantasy football

    • People browse during day, buy in evening

    • Vioxx



Sponsored search today l.jpg
Sponsored search today

  • 2007: ~ $10 billion industry

    • ‘06~$8.5B ‘05~$7B ‘04~$4B ‘03~$2.5B ‘02~$1B

  • $8.7 billion 2007 US ad revenue (41% of US online ads; 2% of all US ads)

  • Resurgence in web search, web advertising

  • Online advertising spending still trailing consumer movement online

  • For many businesses, substitute for eBay

  • Like eBay, mini economy of 3rd party products & services: SEO, SEM


Sponsored search a brief biased history l.jpg
Sponsored SearchA Brief & Biased History

  • Idealab  GoTo.com (no relation to Go.com)

    • Crazy (terrible?) idea, meant to combat search spam

    • Search engine “destination” that ranks results based on who is willing to pay the most

    • With algorithmic SEs out there, who would use it?

  • GoTo   Yahoo! Search Marketing

    • Team w/ algorithmic SE’s, provide “sponsored results”

    • Key: For commercial topics (“LV travel”, “digital camera”) actively searched for, people don’t mind (like?) it

    • Editorial control, “invisible hand” keep results relevant

  • Enter Google

    • Innovative, nimble, fast, effective

    • Licensed Overture patent (one reason for Y!s ~5% stake in G)


Sponsored search a brief biased history21 l.jpg

Thanks: S. Lahaie

Sponsored SearchA Brief & Biased History

  • Overture introduced the first design in 1997: first price, rank by bid

  • Google then began running slot auctions in 2000: second price, rank by revenue (bid * CTR)

  • In 2002, Overture (at this point acquired by Yahoo!) then switched to second-price. Still uses rank by bid; Moving toward rank by revenue


Sponsored search a brief biased history22 l.jpg
Sponsored SearchA Brief & Biased History

  • In the beginning:

    • Exact match, rank by bid, pay per click, human editors

    • Mechanism simple, easy to understand, worked, somewhat ad hoc

  • Today & tomorrow:

    • “AI” match, rank by expected revenue (Google), pay per click/impression/conversion, auto editorial, contextual (AdSense, YPN), local, 2nd price (proxy bid), 3rd party optimizers, budgeting optimization, exploration exploitation, fraud, collusion, more attributes and expressiveness, more automation, personalization/targeting, better understanding (economists, computer scientists)


Sponsored search research a brief biased history l.jpg
Sponsored Search ResearchA Brief & Biased History

  • Circa 2004

    • Weber & Zeng, A model of search intermediaries and paid referrals

    • Bhargava & Feng, Preferential placement in Internet search engines

    • Feng, Bhargava, & PennockImplementing sponsored search in web search engines: Computational evaluation of alternative mechanisms

    • Feng, Optimal allocation mechanisms when bidders’ ranking for objects is common

    • Asdemir, Internet advertising pricing models

    • Asdemir, A theory of bidding in search phrase auctions: Can bidding wars be collusive?

    • Mehta, Saberi, Vazirani, & VaziranAdWords and generalized on-line matching

  • Key papers, survey, and ongoing research workshop series

    • Edelman, Ostrovsky, and Schwarz, Internet Advertising and the Generalized Second Price Auction, 2005

    • Varian, Position Auctions, 2006

    • Lahaie, Pennock, Saberi, Vohra, Sponsored Search, Chapter 28 in Algorithmic Game Theory, Cambridge University Press, 2007

    • 1st-3nd Workshops on Sponsored Search Auctions4th Workshop on Ad Auctions -- Chicago Julu 8-9, 2008


Allocation and pricing l.jpg
Allocation and pricing

  • Allocation

    • Yahoo!: Rank by decreasing bid

    • Google: Rank by decreasing bid * E[CTR] (Rank by decreasing “revenue”)

  • Pricing

    • Pay “next price”: Min price to keep you in current position


Yahoo allocation bid ranking l.jpg
Yahoo Allocation: Bid Ranking

search “las vegas travel”, Yahoo!

“las vegas travel” auction

pays $2.95per click

pays $2.94

pays $1.02

... bidder ipays bidi+1+.01


Google allocation ranking l.jpg
Google Allocation: $ Ranking

“las vegas travel” auction

x E[CTR] = E[RPS]

x E[CTR] = E[RPS]

x E[CTR] = E[RPS]

x E[CTR] = E[RPS]

x E[CTR] = E[RPS]


Google allocation ranking27 l.jpg

TripReservations

Expedia

LVGravityZone

etc...

Google Allocation: $ Ranking

search “las vegas travel”, Google

“las vegas travel” auction

pays 3.01*.1/.2+.01 = 1.51per click

x .1 = .301

x .2 = .588

pays 2.93*.1/.1+.01 = 2.94

x .1 = .293

pays bidi+1*CTRi+1/CTRi+.01

x E[CTR] = E[RPS]

x E[CTR] = E[RPS]


Aside second price auction vickrey auction l.jpg
Aside: Second price auction(Vickrey auction)

  • All buyers submit their bids privately

  • buyer with the highest bid wins;pays the price of the second highest bid

Only pays $120

$150

$120

$90

$50


Incentive compatibility truthfulness l.jpg
Incentive Compatibility(Truthfulness)

  • Telling the truth is optimal in second-price (Vickrey) auction

  • Suppose your value for the item is $100;if you win, your net gain (loss) is $100 - price

  • If you bid more than $100:

    • you increase your chances of winning at price >$100

    • you do not improve your chance of winning for < $100

  • If you bid less than $100:

    • you reduce your chances of winning at price < $100

    • there is no effect on the price you pay if you do win

  • Dominant optimal strategy: bid $100

    • Key: the price you pay is out of your control

  • Vickrey’s Nobel Prize due in large part to this result


Vickrey clark groves vcg l.jpg
Vickrey-Clark-Groves (VCG)

  • Generalization of 2nd price auction

  • Works for arbitrary number of goods, including allowing combination bids

  • Auction procedure:

    • Collect bids

    • Allocate goods to maximize total reported value (goods go to those who claim to value them most)

    • Payments: Each bidder pays her externality;Pays: (sum of everyone else’s value without bidder) - (sum of everyone else’s value with bidder)

  • Incentive compatible (truthful)


Is google pricing vcg l.jpg
Is Google pricing = VCG?

Well, not really …

Put Nobel Prize-winning theories to work.

Google’s unique auction model uses Nobel Prize-winning economic theory to eliminate the winner’s curse – that feeling that you’ve paid too much. While the auction model lets advertisers bid on keywords, the AdWords™ Discounter makes sure that they only pay what they need in order to stay ahead of their nearest competitor.

https://google.com/adsense/afs.pdf


Vcg pricing l.jpg
VCG pricing

  • (sum of everyone else’s value w/o bidder) - (sum of everyone else’s value with bidder)

  • CTRi = advi * posi (key “separability” assumption)

  • pricei = 1/advi*(∑j<ibidj*CTRj + ∑j>ibidj*advj*posj-1 -∑j≠ibidj*CTRj ) = 1/advi*(∑j>ibidj*advj*posj-1 - ∑j>ibidj*CTRj )

  • Notes

    • For truthful Y! ranking set advi = 1. But Y! ranking technically not VCG because not efficient allocation.

    • Last position may require special handling


Next price equilibrium l.jpg
Next-price equilibrium

  • Next-price auction: Not truthful: no dominant strategy

  • What are Nash equilibrium strategies? There are many!

  • Which Nash equilibrium seems “focal” ?

  • Locally envy-free equilibrium[Edelman, Ostrovsky, Schwarz 2005]Symmetric equilibrium[Varian 2006]Fixed point where bidders don’t want to move  or 

    • Bidders first choose the optimal position for them: position i

    • Within range of bids that land them in position i, bidder chooses point of indifference between staying in current position and swapping up with bidder in position i-1

  • Pure strategy (symmetric) Nash equilibrium

  • Intuitive: Squeeze bidder above, but not enough to risk “punishment” from bidder above


Next price equilibrium34 l.jpg
Next-price equilibrium

  • Recursive solution:posi-1*advi*bi = (posi-1-posi)*advi*vi+posi*advi+1*bi+1bi = (posi-1-posi)*advi*vi+posi*advi+1*bi+1 posi-1*advi

  • Nomenclature:Next price = “generalized second price” (GSP)


Ad exchanges35 l.jpg

Ad exchanges

Right Media

Expressiveness


Online advertising evolution l.jpg
Online Advertising Evolution

  • Direct: Publishers sell owned & operated (O&O) inventory

  • Ad networks: Big publishers place ads on affiliate sites, share revenueAOL, Google, Yahoo!, Microsoft

  • Ad exchanges: Match buy orders from advertisers with sell orders from publishers and ad networksKey distinction: exchange does not “own” inventory


Exchange basics l.jpg

Advertisers

Publishers

Netflix

MySpace

Vonage

Demand

Six Apart

Auto.com

Looksmart

Monster

Inventory

Exchange

Networks

Ad.com

CPX

Tribal

[Source: Ryan Christensen]

Exchange Basics


Right media publisher experience l.jpg

[Source: Ryan Christensen]

Right Media Publisher Experience

  • Publisher can select / reject specific advertisers

  • Green = linked network

  • Light Blue = direct advertiser

  • Publishers can traffic their own deals by clicking “Add Advertiser”

The publisher can approve creative from each advertiser


Right media advertiser experience l.jpg

[Source: Ryan Christensen]

Right Media Advertiser Experience

  • Advertisers can set targets for CPM, CPC and CPA campaigns

  • Set budgets and frequency caps

  • Locate publishers, upload creative and traffic campaigns


Expressiveness l.jpg
Expressiveness

  • “I’ll pay 10% more for Males 18-35”

  • “I’ll pay $0.05 per impression, $0.25 per click, and $5.25 per conversion”

  • “I’ll pay 50% more for exclusive display, or w/o Acme”

  • “My marginal value per click is decreasing/increasing”

  • “Never/Always show me next to Acme”“Never/Always show me on adult sites”“Show me when Amazon.com is 1st algo search result”

  • “I need at least 10K impressions, or none”

  • “Spread out my exposure over the month”

  • “I want three exposures per user, at least one in the evening”

Design parameters: Advertiser needs/wants,computational/cognitive complexity, revenue


Expressiveness example l.jpg
Expressiveness Example

  • Competition constraints

b xCTR = RPS

3 x .05 = .15

1 x .05 = .05


Expressiveness example42 l.jpg
Expressiveness Example

monopoly bid

  • Competition constraints

b xCTR = RPS

4 x .07 = .28


Expressiveness design l.jpg
Expressiveness: Design

  • Multi-attribute bidding


Expressiveness less is more l.jpg
Expressiveness: Less is More

  • Pay per conversion: Advertisers pay for user actions (sales, sign ups, extended browsing, ...)

    • Network sends traffic

    • Advertisers rate users/types 0-100Pay in proportion

    • Network learns, optimizes traffic, repeat

  • Fraud: Short-term gain only: If advertisers lie, they stop getting traffic


Expressiveness less is more45 l.jpg
Expressiveness: Less is More

  • “I’m a dry cleaner in Somerset, New Jersey with $100/month. Advertise for me.”

  • Can advertisers trust network to optimize?


Coming convergence ml and mechanism design l.jpg

Stats/ML/OptEngine

Stats/ML/OptEngine

Stats/ML/OptEngine

Stats/ML/OptEngine

Stats/ML/OptEngine

Coming Convergence:ML and Mechanism Design

Mechanism(Rules)

e.g. Auction,Exchange, ...


Ml inner loop l.jpg
ML Inner Loop

  • Optimal allocation (ad-user match) depends on: bid, E[clicks], E[sales], relevance, ad, advertiser, user, context (page, history), ...

  • Expectations must be learned

  • Learning in dynamic setting requires exploration/exploitation tradeoff

  • Mechanism design must factor all this in! Nontrivial.


Selected survey of internet advertising research l.jpg

Selected Survey ofInternet Advertising Research


An analysis of alternative slot auction designs for sponsored search l.jpg

Source: S. Lahaie

An Analysis of Alternative Slot Auction Designs for Sponsored Search

  • Sebastien Lahaie, Harvard University*

  • *work partially conducted at Yahoo! Research

  • ACM Conference on Electronic Commerce, 2006


Objective l.jpg

Source: S. Lahaie

Objective

  • Initiate a systematic study of Yahoo! and Google slot auctions designs.

  • Look at both “short-run” incomplete information case, and “long-run” complete information case.


Outline51 l.jpg

Source: S. Lahaie

Outline

  • Incomplete information (one shot game)

    • Incentives

    • Efficiency

    • Informational requirements

    • Revenue

  • Complete Information (long-run equilibrium)

    • Existence of equilibria

    • Characterization of equilibria

    • Efficiency of equilibria (“price of anarchy”)


The model l.jpg

Source: S. Lahaie

The Model

  • slots, bidders

  • The type of bidder i consists of

    • a value per click of , realization

    • a relevance , realization

  • is bidder i’s revenue, realization

  • Ad in slot is viewed with probability So CTRi,k =

  • Bidder i’s utility function is quasi-linear:


The model cont d l.jpg

Source: S. Lahaie

The Model (cont’d)

  • is i.i.d on according to

  • is continuous and has full support

  • is common knowledge

  • Probabilities are common knowledge.

  • Only bidder i knows realization

  • Both seller and bidder i know , but other bidders do not


Auction formats l.jpg

Source: S. Lahaie

Auction Formats

  • Rank-by-bid (RBB): bidders are ranked according to their declared values ( )

  • Rank-by-revenue (RBR): bidders are ranked according to their declared revenues ( )

  • First-price: a bidder pays his declared value

  • Second-price (next-price): For RBB, pays next highest price. For RBR, pays

  • All payments are per click


Incentives l.jpg

Source: S. Lahaie

Incentives

  • First-price: neither RBB nor RBR is truthful

  • Second-price: being truthful is not a dominant strategy, nor is it an ex post Nash equilibrium (by example):

  • Use Holmstrom’s lemma to derive truthful payment rules for RBB and RBR:

  • RBR with truthful payment rule is VCG


Efficiency l.jpg

Source: S. Lahaie

Efficiency

  • Lemma: In a RBB auction with either a first- or second-price payment rule, the symmetric Bayes-Nash equilibrium bid is strictly increasing with value. For RBR it is strictly increasing with product.

  • RBB is not efficient (by example).

  • Proposition: RBR is efficient (proof).


First price bidding equilibria l.jpg

Source: S. Lahaie

First-Price Bidding Equilibria

  • is the expected resulting clickthrough rate, in a symmetric equilibrium of the RBB auction, to a bidder with value y and relevance 1.

  • is defined similarly for bidder with product y and relevance 1.

  • Proposition: Symmetric Bayes-Nash equilibrium strategies in a first-price RBB and RBR auction are given by, respectively:


Informational requirements l.jpg

Source: S. Lahaie

Informational Requirements

  • RBB: bidder need not know his own relevance, or the distribution over relevance.

  • RBR: must know own relevance and joint distribution over value and relevance.


Revenue ranking l.jpg

Source: S. Lahaie

Revenue Ranking

  • Revenue equivalence principle: auctions that lead to the same allocations in equilibrium have the same expected revenue.

  • Neither RBB nor RBR dominates in terms of revenue, for a fixed number of agents, slots, and a fixed .


Complete information nash equilibria l.jpg

Source: S. Lahaie

Complete Information Nash Equilibria

Argument: a bidder always tries to match the next-lowest bid to minimize costs. But it is not an equilibrium for all to bid 0.

Argument: corollary of characterization lemma.


Characterization of equilibria l.jpg

Source: S. Lahaie

Characterization of Equilibria

  • RBB: same characterization with replacing


Price of anarchy l.jpg

Source: S. Lahaie

Price of Anarchy

Define:


Exponential decay l.jpg

Source: S. Lahaie

Exponential Decay

  • Typical model of decaying clickthrough rate:

  • [Feng et al. ’05] find that their actual clickthrough data is fit well by such a model with

  • In this case


Conclusion l.jpg

Source: S. Lahaie

Conclusion

  • Incomplete information (on-shot game):

    • Neither first- nor second-pricing leads to truthfulness.

    • RBR is efficient, RBB is not

    • RBB has weaker informational requirements

    • Neither RBB nor RBR is revenue-dominant

  • Complete information (long-run equilibrium):

    • First-price leads to no pure strategy Nash equilibria, but second-price has many.

    • Value in equilibrium is constant factor away from “standard” value.


Future work l.jpg

Source: S. Lahaie

Future Work

  • Better characterization of revenue properties: under what conditions on does either RBB or RBR dominate?

  • Revenue results for complete information case (relation to Edelman et al.’s “locally envy-free equilibria”).


Research problem online estimation of clickrates l.jpg

Source: S. Lahaie

Research Problem: Online Estimation of Clickrates

  • Make virtually no assumptions on clickrates.

  • Each different ranking yields (1) information on clickrates and (2) revenue.

  • Tension between optimizing current revenue based on current information, and gaining more info on clickrates to optimize future revenue (multi-armed bandit problem...)

  • Twist: chosen policy determines rankings, which will affect agent’s equilibrium behavior.


Equilibrium revenue simulations of hybrid sponsored search mechanisms l.jpg

Equilibrium revenue simulations of hybrid sponsored search mechanisms

Sebastien Lahaie, Harvard University**work conducted at Yahoo! Research

David Pennock, Yahoo! Research


Revenue effects l.jpg
Revenue effects mechanisms

  • What gives most revenue?

    • Key: If rules change, advertiser bids will change

    • Use Edelman et al. envy-free equilibrium solution

Overture

Highest bid wins

Google/Yahoo!Highest bid*CTR wins

HybridHighest bid*(CTR)s wins

s=0

s=1

s=1/2 ?

s=3/4 ?


Monte carlo simulations l.jpg

Source: S. Lahaie mechanisms

Monte-Carlo simulations

  • 10 bidders, 10 positions

  • Value and relevance are i.i.d. and have lognormal marginals with mean and variance (1,0.2) and (1,0.5) resp.

  • Spearman correlation between value and relevance is varied between -1 and 1.

  • Standard errors are within 2% of plotted estimates.


Slide70 l.jpg

Source: S. Lahaie mechanisms


Slide71 l.jpg

Source: S. Lahaie mechanisms


Slide72 l.jpg

Source: S. Lahaie mechanisms


Preliminary conclusions l.jpg

Source: S. Lahaie mechanisms

Preliminary Conclusions

  • With perfectly negative correlation(-1), revenue, efficiency, and relevance exhibits threshold behavior

  • Squashing up to this threshold can improve revenue without too much sacrifice in efficiency or relevance

  • Squashing can significantly improve revenue with positive correlation


Michael schwarz yahoo research ben edelman harvard university l.jpg

Michael Schwarz mechanisms, Yahoo! Research

Ben Edelman, Harvard University

Source: M. Schwarz

Pragmatic Robots and Equilibrium Bidding in GSP Auctions


Testing game theory l.jpg

Thanks: M. Schwarz mechanisms

Testing game theory

  • Empirical game theory

    • Analytic solutions intractable in all but simplest settings

    • Laboratory experiments cumbersome, costly

    • Agent-based simulation: easy, cheap, allow massive exploration; Key: modeling realistic strategies

  • Ideal for agent-based simulation: when real economic decisions are already delegated to software

    “If pay-per-click marketing is so strategic, how can it be automated? That’s why we developed Rules-Based Bidding. Rules-Based Bidding allows you to apply the kind of rules you would use if you were managing your bids manually.” Atlashttp://www.atlasonepoint.com/products/bidmanager/rulesbased


Bidders actual strategies l.jpg

Source: M. Schwarz mechanisms

Bidders’ actual strategies


Models of gsp l.jpg

Source: M. Schwarz mechanisms

Models of GSP

  • Static game of complete information

  • Generalized English Auction (simple dynamic model)

    More realistic model

  • Each period one random bidder can change his bid

  • Before the move a bidder observes all standing bids


Pragmatic robot pr l.jpg

Source: M. Schwarz mechanisms

Pragmatic Robot (PR)

  • Find current optimal position iImplies range of possible bids: Static best response (BR set)

  • Choose envy-free point inside BR set:Bid up to point of indifference between position i and position i-1

  • If start in equilibrium PRs stay in equilibrium


Convergence of pr simulation l.jpg

Source: M. Schwarz mechanisms

Convergence of PRSimulation


Convergence of pr l.jpg

Source: M. Schwarz mechanisms

Convergence of PR


Convergence of pr81 l.jpg

Source: M. Schwarz mechanisms

Convergence of PR

  • The fact that PR converges supports the assertion that the equilibrium of a simple model informs us about the outcome of intractable dynamic game that inspired it

?

Simple model inspired by a complex game

Complex game that we can not solve


Playing with ideal subjects l.jpg

Source: M. Schwarz mechanisms

Playing with Ideal Subjects

Largest Gap (commercially available strategy)Moves your keyword listing to the largest bid gap within a specified set of positions

Regime One: 15 robots all play Largest Gap

Regime Two: one robot becomes pragmatic

By becoming Pragmatic pay off is up 16%

Other assumptions: values are log normal, mean valuation 1, std dev 0.7 of the underlying normal, bidders move sequentially in random order


Slide83 l.jpg

Source: M. Schwarz mechanisms

ROI

  • Setting ROI target is a popular strategy

  • For any ROI goal the advertiser who switches to pragmatic gets higher payoff


If others play roi targeter l.jpg

Source: M. Schwarz mechanisms

If others play ROI targeter

  • Bidders 1,...,K-1 bid according to the ROI targeting strategy

  • What is K’s best response?


Reinforcement learner vs pragmatic robot l.jpg
Reinforcement Learner mechanismsvs Pragmatic Robot

  • Pragmatic learner outperforms reinforcement learner (that we tried)

  • Remark: reinforcement learning does not converge in a problem with big BR set

Source: M. Schwarz


Conclusion86 l.jpg

Thanks: M. Schwarz mechanisms

Conclusion

  • A strategy inspired by theory seems useful in practice: PR beats commercially available strategies and other reasonable baselines

  • Since PR converges and performs well, the equilibrium concept is sound in spite the fact that some theoretical assumptions are violated and there are plenty of players who are “irrational”

  • When bidding agents are used for real economic decisions (e.g., search engine optimization), we have an ideal playground for empirical game theory simulations


First workshop on sponsored search auctions at acm electronic commerce 2005 l.jpg

First Workshop on Sponsored Search Auctions mechanismsat ACM Electronic Commerce, 2005

Organizers:

Kursad Asdemir, University of AlbertaHemant Bharghava, University of California DavisJane Feng, University of FloridaGary Flake, MicrosoftDavid Pennock, Yahoo! Research


Papers l.jpg
Papers mechanisms

  • Mechanism Design

    • Pay-Per-Percentage of Impressions: An Advertising Method that is Highly Robust to Fraud, J.Goodman

    • Stochastic and Contingent-Payment Auctions, C.Meek,D.M.Chickering, D.B.Wilson

    • Optimize-and-Dispatch Architecture for Expressive Ad Auctions, D.Parkes, T.Sandholm

    • Sponsored Search Auction Design via Machine Learning, M.-F. Balcan, A.Blum, J.D.Hartline, Y.Mansour

    • Knapsack Auctions, G.Aggarwal, J.D. Hartline

    • Designing Share Structure in Auctions of Divisible Goods, J.Chen, D.Liu, A.B.Whinston


Papers89 l.jpg
Papers mechanisms

  • Bidding Strategies

    • Strategic Bidder Behavior in Sponsored Search Auctions, Benjamin Edelman, Michael Ostrovsky

    • A Formal Analysis of Search Auctions Including Predictions on Click Fraud and Bidding Tactics, B.Kitts, P.Laxminarayan, B.LeBlanc, R.Meech

  • User experience

    • Examining Searcher Perceptions of and Interactions with Sponsored Results, B.J.Jansen, M. Resnick

    • Online Advertisers' Bidding Strategies for Search, Experience, and Credence Goods: An Empirical Investigation, A.Animesh, V. Ramachandran, S.Vaswanathan


Stochastic auctions c meek d m chickering d b wilson l.jpg
Stochastic Auctions mechanismsC.Meek,D.M.Chickering, D.B.Wilson

  • Ad ranking allocation rule is stochastic

  • Why?

    • Reduces incentive for “bid jamming”

    • Naturally incorporates explore/exploit mix

    • Incentive for low value bidders to join/stay?

  • Derive truthful pricing rule

  • Investigate contingent-payment auctions:Pay per click, pay per action, etc.

  • Investigate bid jamming, exploration strategies


Expressive ad auctions d parkes t sandholm l.jpg
Expressive Ad Auctions mechanismsD.Parkes, T.Sandholm

  • Propose expressive bidding semantics for ad auctions (examples next)

    • Good: Incr. economic efficiency, incr. revenue

    • Bad: Requires combinatorial optimization;Ads need to be displayed within milliseconds

  • To address computational complexity, propose “optimize and dispatch” architecture: Offline scheduler “tunes” an online (real-time) dispatcher


Expressive bidding i l.jpg
Expressive bidding I mechanisms

  • Multi-attribute bidding


Expressive bidding ii l.jpg
Expressive bidding II mechanisms

  • Competition constraints

b xCTR = RPS

3 x .05 = .15

1 x .05 = .05


Expressive bidding ii94 l.jpg
Expressive bidding II mechanisms

monopoly bid

  • Competition constraints

b xCTR = RPS

4 x .07 = .28


Expressive bidding iii l.jpg
Expressive bidding III mechanisms

  • Guaranteed future delivery

  • Decreasing/increasing marginal value

  • All or nothing bids

  • Pay per: impression, click, action, ...

  • Type/id of distribution site (content match)

  • Complex search query properties

  • Algo results properties (“piggyback bid”)

  • Ad infinitum

  • Keys: What advertisers want; what advertisers value differently; controlling cognitive burden; computational complexity


Second workshop on sponsored search auctions l.jpg

Source: K. Asdemir mechanisms

Second Workshop on Sponsored Search Auctions

Organizing Committee

Kursad Asdemir, University of Alberta

Jason Hartline, Microsoft Research

Brendan Kitts, Microsoft

Chris Meek, Microsoft Research


Objectives l.jpg

Source: K. Asdemir mechanisms

Objectives

  • Diversity

    • Participants

      • Industry: Search engines and search engine marketers

      • Academia: Engineering, business, economics schools

  • Approaches

    • Mechanism Design

    • Empirical

    • Data mining / machine learning

  • New Ideas


  • History overview l.jpg

    Source: K. Asdemir mechanisms

    History & Overview

    • First Workshop on S.S.A.

      • Vancouver, BC 2005

      • ~25 participants

      • 10 papers + Open discussion

      • 4 papers from Microsoft Research

    • Second Workshop on S.S.A.

      • ~40-50 participants

      • 10 papers + Panel

      • 3 papers from Yahoo! Research


    Participants l.jpg

    Source: K. Asdemir mechanisms

    Participants

    • Industry

      • Yahoo!, Microsoft, Google

      • Iprospect (Isobar), Efficient Frontier, HP Labs, Bell Labs, CommerceNet

    • Academia

      • Several schools


    Papers100 l.jpg

    Source: K. Asdemir mechanisms

    Papers

    • Mechanism design

      • Edelman, Ostrovsky, and Schwarz

      • Iyengar and Kumar

      • Liu, Chen, and Whinston

      • Borgs et al.

    • Bidding behavior

      • Zhou and Lukose

      • Szymanski and Lee

      • Asdemir

      • Borgs et al.

    • Data mining

      • Regelson and Fain

      • Sebastian, Bartz, and Murthy


    Panel models of sponsored search what are the right questions l.jpg

    Source: K. Asdemir mechanisms

    Panel: Models of Sponsored Search:What are the Right Questions?

    • Proposed by

      • Lance Fortnow and Rakesh Vohra

    • Panel members

      • Kamal Jain, Microsoft Research

      • Rakesh Vohra, Northwestern University

      • Michael Schwarz, Yahoo! Inc

      • David Pennock, Yahoo! Inc


    Panel discussions l.jpg

    Source: K. Asdemir mechanisms

    Panel Discussions

    • Mechanisms

      • Competition between mechanisms

      • Ambiguity vs Transparency: “Pricing” versus “auctions”

      • Involving searchers

    • Budget

      • Hard or a soft constraint

      • Flighting (How to spend the budget over time?)

    • Pay-per-what? CPM, CPC, CPS

      • Risk sharing

      • Fraud resistance

    • Transcript available!


    Web resources l.jpg
    Web resources mechanisms

    • 1st Workshop website & papers:http://research.yahoo.com/workshops/ssa2005/

    • 1st Workshop notes (by Rohit Khare):http://wiki.commerce.net/wiki/RK_SSA_WS_Notes

    • 2nd Workshop website & papers:http://www.bus.ualberta.ca/kasdemir/ssa2/

    • 2nd Workshop panel transcript:(thanks Hartline & friends!)http://research.microsoft.com/~hartline/papers/panel-SSA-06.pdf

    • 3rd Workshop websitehttp://opim-sun.wharton.upenn.edu/ssa3/index.html

    • 4th Workshop websitehttp://research.yahoo.com/workshops/adauctions2008/


    More challenges l.jpg
    More Challenges mechanisms

    • Unifying search, display, content, offline

    • Economics of attention

    • Directly rewarding users, control, privacy3-party game theoretic equilibrium

    • Predicting click through rates

    • Detecting spam/fraud

    • Pay per “action” / conversion

    • Number/location/size of of ads

    • Improved targeting / expressiveness

    • $15B Question: Monetizing social networks, user-generated content


    Prediction markets l.jpg

    Prediction Markets mechanisms

    David Pennock, Yahoo! Research


    Bet credible opinion l.jpg
    Bet = Credible Opinion mechanisms

    Obama will win the 2008 US Presidential election

    • Which is more believable?More Informative?

    • Betting intermediaries

      • Las Vegas, Wall Street, Betfair, Intrade,...

      • Prices: stable consensus of a large number of quantitative, credible opinions

      • Excellent empirical track record

    “I bet $100 Obama will win at 1 to 2 odds”


    A prediction market l.jpg
    A Prediction Market mechanisms

    • Take a random variable, e.g.

    • Turn it into a financial instrument payoff = realized value of variable

    Bird Flu Outbreak US 2008?(Y/N)

    I am entitled to:

    Bird FluUS ’08

    Bird FluUS ’08

    $1 if

    $0 if


    Slide108 l.jpg

    http://intrade.com mechanisms


    Prediction markets examples research l.jpg

    Prediction Markets: mechanismsExamples & Research


    The wisdom of crowds backed in dollars l.jpg

    What you can say/learn mechanisms% chance that

    Obama wins

    GOP wins Texas

    YHOO stock > 30

    Duke wins tourney

    Oil prices fall

    Heat index rises

    Hurricane hits Florida

    Rains at place/time

    Where

    IEM, Intrade.com

    Intrade.com

    Stock options market

    Las Vegas, Betfair

    Futures market

    Weather derivatives

    Insurance company

    Weatherbill.com

    The Wisdom of CrowdsBacked in dollars


    Prediction markets with money without l.jpg
    Prediction Markets mechanismsWith Money Without


    The widsom of crowds backed in points l.jpg
    The Widsom of Crowds mechanismsBacked in “Points”

    • HSX.com

    • Newsfutures.com

    • InklingMarkets.com

    • Foresight Exchange

    • CasualObserver.net

    • FTPredict.com

    • Yahoo!/O’Reilly Tech Buzz

    • ProTrade.com

    • StorageMarkets.com

    • TheSimExchange.com

    • TheWSX.com

    • Alexadex, Celebdaq, Cenimar, BetBubble, Betocracy, CrowdIQ, MediaMammon,Owise, PublicGyan, RIMDEX, Smarkets, Trendio, TwoCrowds

    • http://www.chrisfmasse.com/3/3/markets/#Play-Money_Prediction_Markets


    Slide113 l.jpg

    http://betfair.com mechanisms

    Screen capture 2008/05/07

    http://tradesports.com

    Screen capture 2007/05/18


    Example iem 1992 l.jpg

    [Source: Berg, DARPA Workshop, 2002] mechanisms

    Example: IEM 1992


    Example iem l.jpg

    [Source: Berg, DARPA Workshop, 2002] mechanisms

    Example: IEM


    Example iem116 l.jpg

    [Source: Berg, DARPA Workshop, 2002] mechanisms

    Example: IEM


    Does it work l.jpg

    [Thanks: Yiling Chen] mechanisms

    Does it work?

    • Yes, evidence from real markets, laboratory experiments, and theory

      • Racetrack odds beat track experts [Figlewski 1979]

      • Orange Juice futures improve weather forecast [Roll 1984]

      • I.E.M. beat political polls 451/596 [Forsythe 1992, 1999][Oliven 1995][Rietz 1998][Berg 2001][Pennock 2002]

      • HP market beat sales forecast 6/8 [Plott 2000]

      • Sports betting markets provide accurate forecasts of game outcomes [Gandar 1998][Thaler 1988][Debnath EC’03][Schmidt 2002]

      • Laboratory experiments confirm information aggregation[Plott 1982;1988;1997][Forsythe 1990][Chen, EC’01]

      • Theory: “rational expectations” [Grossman 1981][Lucas 1972]

      • Market games work [Servan-Schreiber 2004][Pennock 2001]


    Prediction markets does money matter l.jpg

    Prediction Markets: mechanismsDoes Money Matter?


    The wisdom of crowds with money without l.jpg

    IEM: 237 Candidates mechanisms

    HSX: 489 Movies

    The Wisdom of CrowdsWith Money Without


    The wisdom of crowds with money without120 l.jpg
    The Wisdom of Crowds mechanismsWith Money Without


    Real markets vs market games l.jpg

    probabilistic mechanismsforecasts

    Real markets vs. market games

    HSX

    FX, F1P6

    forecast source avg log score

    F1P6 linear scoring -1.84

    F1P6 F1-style scoring -1.82

    betting odds -1.86

    F1P6 flat scoring -2.03

    F1P6 winner scoring -2.32


    Does money matter play vs real head to head l.jpg

    Experiment mechanisms

    2003 NFL Season

    ProbabilitySports.com Online football forecasting competition

    Contestants assess probabilities for each game

    Quadratic scoring rule

    ~2,000 “experts”, plus:

    NewsFutures (play $)

    Tradesports (real $)

    Used “last trade” prices

    Results:

    Play money and real money performed similarly

    6th and 8th respectively

    Markets beat most of the ~2,000 contestants

    Average of experts came 39th (caveat)

    Does money matter? Play vs real, head to head

    Electronic Markets, Emile Servan-Schreiber, Justin Wolfers, David Pennock and Brian Galebach


    Does money matter play vs real head to head124 l.jpg
    Does money matter? mechanismsPlay vs real, head to head

    Statistically:TS ~ NFNF >> Avg

    TS > Avg


    A problem w virtual currency printing money l.jpg
    A Problem w/ Virtual Currency mechanismsPrinting Money

    Alice1000

    Betty1000

    Carol1000


    A problem w virtual currency printing money126 l.jpg
    A Problem w/ Virtual Currency mechanismsPrinting Money

    Alice5000

    Betty1000

    Carol1000


    Yootles a social currency l.jpg
    Yootles mechanismsA Social Currency

    Alice0

    Betty0

    Carol0


    Yootles a social currency128 l.jpg
    Yootles mechanismsA Social Currency

    I owe you 5

    Alice-5

    Betty0

    Carol5


    Yootles a social currency129 l.jpg
    Yootles mechanismsA Social Currency

    I owe you 5

    credit: 5

    credit: 10

    Alice-5

    Betty0

    Carol5


    Yootles a social currency130 l.jpg
    Yootles mechanismsA Social Currency

    I owe you 5

    I owe you 5

    credit: 5

    credit: 10

    Alice-5

    Betty0

    Carol5


    Yootles a social currency131 l.jpg
    Yootles mechanismsA Social Currency

    I owe you 5

    I owe you 5

    credit: 5

    credit: 10

    Alice3995

    Betty0

    Carol5


    Yootles a social currency132 l.jpg
    Yootles mechanismsA Social Currency

    • For tracking gratitude among friends

    • A yootle says “thanks, I owe you one”



    Combinatorics example march madness l.jpg
    Combinatorics Example mechanismsMarch Madness


    Combinatorics example march madness135 l.jpg

    Typical today mechanismsNon-combinatorial

    Team wins Rnd 1

    Team wins Tourney

    A few other “props”

    Everything explicit(By def, small #)

    Every bet indep: Ignores logical & probabilistic relationships

    Combinatorial

    Any property

    Team wins Rnd kDuke > {UNC,NCST}ACC wins 5 games

    2264 possible props(implicitly defined)

    1 Bet effects related bets “correctly”;e.g., to enforce logical constraints

    Combinatorics ExampleMarch Madness


    Expressiveness getting information l.jpg
    Expressiveness: mechanismsGetting Information

    • Things you can say today:

      • (43% chance that) Hillary wins

      • GOP wins Texas

      • YHOO stock > 30 Dec 2007

      • Duke wins NCAA tourney

    • Things you can’t say (very well) today:

      • Oil down, DOW up, & Hillary wins

      • Hillary wins election, given that she wins OH & FL

      • YHOO btw 25.8 & 32.5 Dec 2007

      • #1 seeds in NCAA tourney win more than #2 seeds


    Expressiveness processing information l.jpg
    Expressiveness: mechanismsProcessing Information

    • Independent markets today:

      • Horse race win, place, & show pools

      • Stock options at different strike prices

      • Every game/proposition in NCAA tourney

      • Almost everything: Stocks, wagers, intrade, ...

    • Information flow (inference) left up to traders

    • Better: Let traders focus on predicting whatever they want, however they want: Mechanism takes care of logical/probabilistic inference

    • Another advantage: Smarter budgeting


    Automated market makers l.jpg

    [Thanks: Yiling Chen] mechanisms

    Automated Market Makers

    • A market maker (a.k.a. bookmaker) is a firm or person who is almost always willing to accept both buy and sell orders at some prices

    • Why an institutional market maker? Liquidity!

      • Without market makers, the more expressive the betting mechanism is the less liquid the market is (few exact matches)

      • Illiquidity discourages trading: Chicken and egg

      • Subsidizes information gathering and aggregation: Circumvents no-trade theorems

    • Market makers, unlike auctioneers, bear risk. Thus, we desire mechanisms that can bound the loss of market makers

      • Market scoring rules [Hanson 2002, 2003, 2006]

      • Dynamic pari-mutuel market [Pennock 2004]





    Mech design for prediction142 l.jpg

    Standard Properties mechanisms

    Efficiency

    Inidiv. rationality

    Budget balance

    Revenue

    Truthful (IC)

    Comp. complexity

    Equilibrium

    General, Nash, ...

    PM Properties

    #1: Info aggregation

    Expressiveness

    Liquidity

    Bounded budget

    Truthful (IC)

    Indiv. rationality

    Comp. complexity

    Equilibrium

    Rational expectations

    Mech Design for Prediction

    Competes with:experts, scoringrules, opinionpools, ML/stats,polls, Delphi


    Discussion l.jpg
    Discussion mechanisms

    • Are incentives for virtual currency strong enough?

      • Yes (to a degree)

      • Conjecture: Enough to get what people already know; not enough to motivate independent research

      • Reduced incentive for information discovery possibly balanced by better interpersonal weighting

    • Statistical validations show HSX, FX, NF are reliable sources for forecasts

      • HSX predictions >= expert predictions

      • Combining sources can help


    Catalysts l.jpg
    Catalysts mechanisms

    • Markets have long history of predictive accuracy: why catching on now as tool?

    • No press is bad press: Policy Analysis Market (“terror futures”)

    • Surowiecki's “Wisdom of Crowds”

    • Companies:

      • Google, Microsoft, Yahoo!; CrowdIQ, HSX, InklingMarkets, NewsFutures

    • Press: BusinessWeek, CBS News, Economist, NYTimes, Time, WSJ, ...http://us.newsfutures.com/home/articles.html


    Cftc role l.jpg
    CFTC Role mechanisms

    • MayDay 2008: CFTC asks for help

    • Q: What to do with prediction markets?

    • Right now, the biggest prediction markets are overseas, academic (1), or just for fun

    • CFTC may clarify, drive innovation

    • Or not


    Conclusion146 l.jpg
    Conclusion mechanisms

    • Prediction Markets:hammer = market, nail = prediction

      • Great empirical successes

      • Momentum in academia and industry

      • Fascinating (algorithmic) mechanism design questions, including combinatorial betting

    • Points-paid peers produce prettygood predictions