Upload
others
View
4
Download
0
Embed Size (px)
Citation preview
Slide 1Sponsored Search Tutorial ACM EC’07
Sponsored Search Tutorial
Yahoo IncThe Wharton SchoolMichael SchwarzKartik Hosanagar
Slide 2Sponsored Search Tutorial ACM EC’07
Outline
“Science will replace much of the art of marketing” – Eric SchmidtIntroduction
Online Advertising and SEM basicsSearch Engine Perspective in SEM
Mechanism Design and Auction RulesChallengesClick Fraud
Advertiser PerspectiveKeyphrase GenerationBidding
Sponsored Search with ContextEmpirical Issues in Sponsored SearchConclusions
Slide 3Sponsored Search Tutorial ACM EC’07
Introduction
Slide 4Sponsored Search Tutorial ACM EC’07
Traditional Advertising
Print, TV, Radio, Direct MailAd agencies buy media on behalf of firms
Dominated by large holding companies (Omnicom, WPP, InterPublic, Publicis Groupe)Individual agencies like JWT, Ogilvy & Mather, McCann Erickson manage brandingLow barriers to entry (talent and sales)» But some economies of scale
Local Advertising (YPs)Publisher centric
Slide 5Sponsored Search Tutorial ACM EC’07
Traditional Advertising
PricingTraditionally fixed commissionsLater negotiated commissionsRecently, labor-based + performance-based» Pushed by advertisers: aligns incentives» Reflects growth in promotions, eevent marketing, product
placement
Slide 6Sponsored Search Tutorial ACM EC’07
Advertising spend
Media 2006
Newspapers 47Direct Mail 56Broadcast TV 45Radio 20Cable TV 22Magazine 16Yellow Pages 15Internet 17TOTAL 238
Slide 7Sponsored Search Tutorial ACM EC’07
Online advertising
Banner ads (Doubleclick)Standardized ad shapes with imagesLoosely related to content
Search linked ads (Google Adwords)Related to search terms
Context linked ads (Google AdSense)Related to content on pageClosely tied to Google’s existing competence on figuring out what a page is really about
Slide 8Sponsored Search Tutorial ACM EC’07
Search Engine Marketing (SEM)
Searchresults
Sponsoredad
Sponsored
ads
Slide 9Sponsored Search Tutorial ACM EC’07
Search Engine Marketing
High relevance (based on user context)Occurs close to decision/buying timeHighly measurableResults in very good performance in cost-per-acquisition (adv expenditure per sale)Rapid growth but still small part of advertising market
Total US adv spend ~ $220-240 billion, growth ~ 1-2% per yearOnline advertising: ~ $17 billion, growth ~ 35% last year
Slide 10Sponsored Search Tutorial ACM EC’07
Google Valuation
Slide 11Sponsored Search Tutorial ACM EC’07
Information Retrieval (IR)
crawl theweb
Create an invertedindex
Check for duplicates,store the documents
Inverted index
Search engine servers
userquery
Show results To user
DocsCrawlermachines
Source: Marti Hearst (SIMS, UC Berkeley)
Slide 12Sponsored Search Tutorial ACM EC’07
Share of Searches
Organic Traffic is a key to driving SEM revenues
Source: Search Engine Watch (2006)
Slide 13Sponsored Search Tutorial ACM EC’07
How does SEM work?
Search engines run keyword auctions to sell available inventory of ad positions
Advertisers submit bids which indicate their willingness-to-pay per click» for example, bid of $2.10 per click for the keyword “laptop”
The search engine orders the ads in descending orderBid is a key determinant of ad positionOther factors such as CTR are also factored in» More on the mechanism later
Slide 14Sponsored Search Tutorial ACM EC’07
Search Engine Perspective
Slide 15Sponsored Search Tutorial ACM EC’07
The Advertiser Perspective
Slide 16Sponsored Search Tutorial ACM EC’07
Advertiser Perspective
Choose keywordsSet budget
Budgets are commonly observedProxies for inventory constraints, short-term capital constraints, etcSometimes, to protect against click-fraud
Determine bid (maxCPC) for each keywordAuctions not incentive compatibleBudget constraints may restrict bidding strategies
Role of SEM firms
Slide 17Sponsored Search Tutorial ACM EC’07
Keyphrase Generation
Slide 18Sponsored Search Tutorial ACM EC’07
Current Methods
Query log and Advertiser log miningMine query logs and logs of advertiser searches» Google and Yahoo
Mine other keyphrases advertisers have bid on» Yahoo
Proximity searchMeta-tag spidering
Extract meta-tags from top web pages related to seed keywordWord tracker
Terms Net (Joshi and Motwani 2006)Based on semantic similarity between keyphrases
Slide 19Sponsored Search Tutorial ACM EC’07
Semantic Techniques for Keyphrase Generation
An automated system for relevant keyword generation.
Three Steps:Dictionary CreationSemantic SimilarityKeyword Suggestion
Slide 20Sponsored Search Tutorial ACM EC’07
Dictionary Creation
Slide 21Sponsored Search Tutorial ACM EC’07
Semantic Similarity
Dictionary
Hair
Skin
….
Search the web for the term x
xDocument 1
Document 2
…
Search Results
Create L2 Normalized vector for x - QE(x)
Create L2 Normalized vector for y – QE(y)
( , ) ( ). ( )K x y QE x QE y=
Compute Similarity using cosine measure
Slide 22Sponsored Search Tutorial ACM EC’07
Keyword Generation
Construct similarity graph using the association matrix.
Edge weight inversely related to similarity score
Traverse the graph using the watershed algorithm.Assumption – words with lower frequency are cheaper.
Slide 23Sponsored Search Tutorial ACM EC’07
Examples
skin
shavingconditionerwrinkles
agingmakeupdermal
naturalacid peelsoccitane
permanent makeupfree cosmeticsexfoliator
treatment glycolicwrinklesdermal
microdermabrasionskin smoothcare
healthcarescalp skinface
massageskin smoothtreatment
hair removalscalp skinfacial
aromatherapybodyskincare
Slide 24Sponsored Search Tutorial ACM EC’07
Metrics
Precision: Fraction of keyphrase recommendations that are deemed relevantRecall: Fraction of relevant keyphrases identified by system
Universe of relevant keyphrases is unknownRelative measures can be obtained by implementing multiple keyphrase generation techniques» Treat union of relevant recommendations as the universe
Other economic criteria observed empiricallyChanges in revenues, profits, average CPC, etc
Slide 25Sponsored Search Tutorial ACM EC’07
Budget Constrained Bidding
Slide 26Sponsored Search Tutorial ACM EC’07
A Toy Problem
The advertiser has a daily budget of $1000
She is considering bidding on four keywords LaptopRefurbished LaptopHP LaptopSony Laptop
Assume the bids submitted by competitors are known to the advertiser
How should the advertiser bid to get the maximum number of clicks (visitors from the search engine ads) each day?
In real life 1,000s of keywords and millions of $ per month…
Slide 27Sponsored Search Tutorial ACM EC’07
Bid Landscape($ per click)
Advertiser i’s view of other advertisers’ bids for the same keywordsfound via query of Yahoo or Google’s advertising bid database
0.390.400.540.9580.430.400.571.1370.460.420.771.4260.580.510.781.5650.700.550.791.7040.840.560.802.0030.850.580.956.7220.930.591.296.731
Sony LaptopHP LaptopRefurbished
LaptopLaptopSlot
Slide 28Sponsored Search Tutorial ACM EC’07
Expected number of clicks for each keyword and slot
443514685649204778692866
10129640151416135561419231897853273226410992384537015391
Sony LaptopHP LaptopRefurbished
LaptopLaptopSlot
Advertiser i’s view of the benefit of obtaining a given slot for a keywordfound via query of Yahoo or Google’s advertising bid databaseand through advertiser’s own historical clickthrough data
Slide 29Sponsored Search Tutorial ACM EC’07
Tradeoffs to make when deciding what to bid?
ClicksBidClicksBidClicksBidClicksBid
0.39
0.43
0.46
0.58
0.70
0.84
0.85
0.93
0.40
0.40
0.42
0.51
0.55
0.56
0.58
0.59
0.54
0.57
0.77
0.78
0.79
0.80
0.95
1.29
0.95
1.13
1.42
1.56
1.70
2.00
6.72
6.73
44351468564920477869286610129640151416135561419231897853273226410992384537015391
Sony LaptopHP LaptopRefurbished
LaptopLaptopSlot
Slide 30Sponsored Search Tutorial ACM EC’07
Problem formulation
Decision variableshow much to bid on each of four keywords
Objective functionmaximize total number of clicks
Constraintsbudget – maximum $1,000 spentassignment constraints» at most one bid for each key word
Slide 31Sponsored Search Tutorial ACM EC’07
Decision variables and objective for the problem
Decision Variables
xij = 1 if slot i is assigned to keyword j, 0 otherwise;
where i = 1, 2, ..., 8 represents the eight slots and j = A, B, C, D represents the 4 keywords.
Objective Function
Max 1539x1A + 370x1B + 45x1C + 38x1D + 1099x2A + . . . + 4x8C + 4x8D
Slide 32Sponsored Search Tutorial ACM EC’07
Constraints for the IP
Each keyword must be assigned to one, and only one slot:x1A + x2A + x3A + … + x8A ≤ 1 (Keyword A)x1B + x2B + x3B + … + x8B ≤ 1 (Keyword B):
x1D + x2D + x3D + … + x8D ≤ 1 (Keyword J)
Total Budget for the day = $1000:x1A.b1A + x1B.b1B + . . . + x8D.b8D ≤ 1000
where bij is 1 cent more than the bid of the advertiser currently ranked i for keyword j
Integralityxij are all either 0 or 1
Slide 33Sponsored Search Tutorial ACM EC’07
Issues with Formulation?
Bid landscape typically unknownClicks Vs Position unknownKeywords are not of same quality
Conversions matterIP not scalable
Slide 34Sponsored Search Tutorial ACM EC’07
Approach 2: Knapsack
Knapsack problem and greedy heuristicAdaptive algorithm for keyword selection (Paat R* & Williamson)
Static model: case where the CTR for the keywords is known» Sort keywords in descending order of profit/cost. » Choose keywords in descending order (of profit/cost) until the
expected cost is close to the budget. Adaptive algorithm works when CTR is not known apriori» Use data gathered in the first few periods to estimate the CTR
Issues: Does not account for slots
Slide 35Sponsored Search Tutorial ACM EC’07
Other Techniques for Bidding
Online knapsack Problem (Chakrabarty et al. 2007)Stochastic bidding (Muthukrishnan et al. 2007)Efficient Frontier (Holthausen and Assmus 1982)Convex Programming: Scalable and accounts for slots (Hosanagar and Stavrinides 2006)
Slide 36Sponsored Search Tutorial ACM EC’07
Role of Machine Learning
“Standard” Optimization techniques solve deterministic problemsEven stochastic optimization techniques generally assume parameters can be estimatedParameters
Bid-RankRank- ClicksClicks-ConversionsBid-CPC
Slide 37Sponsored Search Tutorial ACM EC’07
Impressions Clicks CostMetrics:Metrics:
Role of Machine Learning
Conversions
Slide 38Sponsored Search Tutorial ACM EC’07
Real-world Complexities
“Exact match”Competing with other advertisers you do not know of
“Broad Match”Your rank changes based on the search query
Data IntegrityImpressions < clicksCPC > Bid
Data Sparseness
Slide 39Sponsored Search Tutorial ACM EC’07
Understanding the Role of SEM Firms
SEM firms use a variety of techniques toIdentify keywords to bid onBid for each keywordProvide metrics
Unable to easily generate business onlineSearch auctions are too complex for many advertisersBidding Blindly on Search EnginesRoI hard to measurePublishers User-centric, not business-centric
Advertiser
Slide 40Sponsored Search Tutorial ACM EC’07
Aggregating the fragmented search channels
Online UsersOnline Users
SEM Firms’ Value Proposition
SEMSEM
Slide 41Sponsored Search Tutorial ACM EC’07
Generating Keywords
ConfigureConfigure»»
Keywords Createdcholesterolheart medicationblood pressure medicationaspirindiabetes dietobesityelectric help in philadelphia
Slide 42Sponsored Search Tutorial ACM EC’07
Determining Bids
2331Expected Position
0.930.591.296.73Bid
Heart Medication
Lipid Reduction
Blood PressureCholesterolSlot
Slide 43Sponsored Search Tutorial ACM EC’07
Conversion > Conversion > Phone calls, emails or Phone calls, emails or conversion pages (forms) conversion pages (forms)
Measuring Conversions
Slide 44Sponsored Search Tutorial ACM EC’07
Key Metrics
Key LeversOrganic traffic:
Metrics: monitor number of pages indexed (benchmark against competitors and look at trends), pagerank (changes slowly), weekly/monthly rank on search engines for your keyword universe (avg, weighted avg pos)
Paid traffic?
Slide 45Sponsored Search Tutorial ACM EC’07
Impressions Clicks CostMetrics:Metrics:
Key Metrics
Conversions
Slide 46Sponsored Search Tutorial ACM EC’07
Key Metrics
Cost Per Click (CPC) or Per Conversion by Search EngineThese should be similar
Conversion Quality by Search EnginesDetermines bid intensity
Click/conversion Volume GeneratedBreak down by source
Average Position (Rank) by CategoryAlign with marketing goals
» Branding (firm level)» Promoting specific prod lines» LTV of customer» Revenues» Margins
Slide 47Sponsored Search Tutorial ACM EC’07
Sponsored Search with Contexts
Slide 48Sponsored Search Tutorial ACM EC’07
Sponsored Search with Contexts
Context: “any auxillary information that might accompany a search, and might include information that is factual, estimated or inferred. Natural examples of contexts include the zip code, gender, or abstract “intentions”…”(Even-dar et al. 2007)Real-world examples
Bid on “dentist” but have different bids for different regions (identified by IP addresses)Retailer bids on clothing but places higher premium on women under 30
Slide 49Sponsored Search Tutorial ACM EC’07
Local Advertising Market
Local Online Searches (per month)
Context-based Auctions: Market Opportunity
$ 100 B$ 100 B
220 M220 M
$18B YP market$18B YP market
$ by Medium
-
2,000.00
4,000.00
6,000.00
8,000.00
10,000.00
12,000.00
14,000.00
16,000.00
2005 2006 2007 2008 2009
$ (m
m)
YP Print
Local Search
Consumer References (in bb)
0
5,000
10,000
15,000
20,000
25,000
2004 2005 2006 2007 2008 2009
Que
ries
Local SearchYP Print
Online searches 50% paOnline searches 50% pa
Consumer Searches (in MM)
Src: SES 2006
Slide 50Sponsored Search Tutorial ACM EC’07
Examples
Slide 51Sponsored Search Tutorial ACM EC’07
Select Context
Slide 52Sponsored Search Tutorial ACM EC’07
Select Budget
Slide 53Sponsored Search Tutorial ACM EC’07
Keyword Creation
Automatically Automatically ConfiguresConfigures»»
Keywords Createdconstruction electrician philadelphia paelectrician in philadelphiaconstruction electricians philadelphiaelectrical contractor website in philadelphiacommercial electricians in philadelphia construction electrician in philadelphiacertified electricians philadelphia pacommercial electricians in philadelphiaelectrical utility contractor philadelphiacommercial electricians philadelphiaelectric help for systems philadelphia paconstruction electricians philadelphia pacertified electricians philadelphia pennsylvaniacertified electrician philadelphiaelectrical contractor website philadelphia electric help in philadelphia
Slide 54Sponsored Search Tutorial ACM EC’07
Internet and Local
Results from Even-Dar et al. (2007): Overall social welfare (advertiser and auctioneer surplus) increases when moving from standard to context-based auctions
However, one party can benefit at the expense of the otherBroader Implications of Context-based Auctions
YP market is fundamentally changingMany YPs have launched online YPs (superpages.com)» But search driving most of the traffic
Slide 55Sponsored Search Tutorial ACM EC’07
Empirical Issues in Sponsored Search
Slide 56Sponsored Search Tutorial ACM EC’07
Synthetic Bid Generation
Ganchev et al. (2007) study bids placed in Yahoo’s (old) open auction
Slide 57Sponsored Search Tutorial ACM EC’07
Traditional Distributions did not do well in generating realistic synthetic bids
Observe significant jamming (bid differences of 1c)
Slide 58Sponsored Search Tutorial ACM EC’07
Clicks Estimation
Ali and Scarr (2007) estimate clicks using data from Yahoo
Use Negative Binomial, Zipf, Zipf-Mandelbrot, Zero-Altered, Zero-Inflated mixture modelsFinding: Zipf-Mandelbrot (ZM) and Zero-Adjusted ZM are effective in modeling clicks distribution
Slide 59Sponsored Search Tutorial ACM EC’07
Estimating CTR for new Ads
Search engine needs to estimate CTR of new ad in order to place itHard to estimate in the absence of historical dataRichardson et al. (2007) run a logistic regression to estimate probability of click
Factors» CTR for other ads (for same keyword)» CTR for related terms (subset of superset of terms)» Ad Quality (appropriate capitalization, use of punctuation, etc)
Each factor helped improve fit by 20% or more
Slide 60Sponsored Search Tutorial ACM EC’07
Conclusions
Several Challenges and Open QuestionsMechanism Design» What are the best rules for ranking, payment» Open versus opaque auction
Bid Optimization» Combinatorial Problem» Stochastic
Keyphrase Generation» Machine Learning
Empirical Studies» Behavior Modeling: Estimating clicks, conversions» Estimating clicks and other functional relationships
Slide 61Sponsored Search Tutorial ACM EC’07
Conclusions
Search Engine Marketing is an interdisciplinary fieldEconomics (Mechanism Design)Computer Science (Algorithms, Machine Learning)Statistics (Resolving uncertainty)Marketing (Modeling Consumer Behavior)
Slide 62Sponsored Search Tutorial ACM EC’07
References
Ali, K. and Scarr, M. 2007. Robust methodologies for modeling web click distributions. In Proceedings of the 16th international Conference on World Wide Web (Banff, Alberta, Canada, May 08 - 12, 2007). Deeparnab Chakrabarty, Yunhong Zhou and Rajan Lukose “Budget constrained bidding in Keyword Auctions and Online Knapsack problems", Third workshop on Sponsored Search, Banff 2007.E. Even-Dar, J. Wortman and M. Kearns, “Sponsored Search with Contexts”, Third Workshop on Sponsored Search Auctions, WWW 2007.K. Ganchev, A. Kulesza, J. Tan, R. Gabbard, Q. Liu. Empirical Price Modeling for Sponsored Search. Third Workshop on Sponsored Search Auctions, WWW 2007. Holthausen, D and G. Assmus, "Advertising Budget Allocation Under Uncertainty," Management Science, 28 (May 1982), 487-499.K. Hosanagar and P. Stavrinides, “Optimal Bidding in Online Slot Auctions”, First International Symposium of Information Systems, Indian School of Business, Hyderabad, India.
Slide 63Sponsored Search Tutorial ACM EC’07
Reeferences
A. Joshi and R. Motwani, "Keyword Generation for Search Engine Advertising", Workshop Proceedings of IEEE ICDM 2006, December 2006Muthukrishnan, S.; Pal, Martin; Svitkina, Zoya, “Stochastic Models for Budget Optimization in Search-Based Advertising “,Third workshop on Sponsored Search, Banff 2007.Richardson, M., Dominowska, E., and Ragno, R. 2007. Predicting clicks: estimating the click-through rate for new ads. In Proceedings of the 16th international Conference on World Wide Web (Banff, Alberta, Canada, May 08 - 12, 2007). P. Rusmevichientong and D. P. Williamson, ``An Adaptive Algorithm for Selecting Profitable Keywords for Search-Based Advertising Services,'' Proceedings of the Seventh ACM Conference on Electronic Commerce, pp. 260-269, 2006.