SlideShare a Scribd company logo
1 of 13
Download to read offline
BRIDGING THE GAP BETWEEN MTA
& PROGRAMMATIC BID OPTIMIZATION
October 17, 2019
1
2
SPEAKERS
JOY JOSEPH
Head- Data & Analytic Services
GroupM
TIM SMITH
Senior Director, Business Development
The Trade Desk
3
MTA VS. PROGRAMMATIC
OPPOSITE BANKS OF THE RIVER?
MTA vs. born out of need to better understand the impact each advertising touchpoint has on outcomes-
• More holistic measurement and optimization of campaign execution
• Rich insights around audience characteristics and their responsiveness across a spectrum of media
journeys and creative components
• More explanatory than predictive
• In-flight course correction of campaign investment strategy- often at no more than a weekly cadence
Programmatic bid optimization was born out of the need for high predictive accuracy, and needs to be able
to optimize several bidding decisions per second-
• Deliver outcomes rather than explain outcomes
• High dimensionality- optimize in real-time across multiple bidding decisions per second
• Update models in real-time to increase sensitivity to short-term audience propensity shifts
4
DEFINING THE GAP
Marketing Objective MTA Programmatic Bid
Optimization
Drive campaign goals by identifying opportunities to optimize efficiency of
addressable marketing spend across channels, journey stages, & audience
X
Understand the fractional impact of each touchpoint within the journey on
conversions
X
Cross-channel addressable investment strategy & optimization (channels,
supply-side platforms/publishers, creative, placements)
X
Achieve in-channel campaign performance by optimizing real-time spend
allocation at an impression level
X
Determine optimal bids across ad inventory attributes to drive campaign KPIs X
Identify the most effective paths to conversion (frequency & sequencing) X
Drive reach or target custom audiences with an extremely high level of
predictive accuracy to obtain higher returns on their advertising spend
X
5
A CRASH COURSE IN PROGRAMMATIC BIDDING ALGOS
Bid decisioning algorithms drive a complex process that:
• Translate bidding strategy into quantified bid factors
• Optimize bid factors using real-time predictions on campaign KPIs
• Prioritize across competing internal bids and submit the bid most likely to win
For instance, The Trade Desk evaluates 10 Million Impressions per second.
For each of these impressions, The Trade Desk uses a unique bid factoring methodology that offer traders
advanced optimization capabilities to narrow targeting and pay the right price by using multiple triggers including
time of day, device, ad format and recency.
Basically, traders input a bidding strategy based on brand goals and the algorithm tests and optimizes it.
However, bidding strategies are set at the aggregate audience segment level rather than user-level, resulting in
lower specificity in bidding vs. true user-level bid optimization.
6
USER-LEVEL BIDS VS. SEGMENT BIDDING
Segment 1
Bid Multiplier = 0.9
Segment 2
Bid Multiplier = 1.1
Segment 3
Segment 3
1.3
1.1
1.2
1.0
1.4
7
WE NEEDED…
A real-time user level scoring system to enhance
programmatic bid optimization algorithms.
CUSTOMER BID SCORING
Use log level data to develop and apply scores for each individual prospect to attain maximum expressiveness
Browsing
Behavior
Geography /
Temperature
Time & DOW
Page Visits
POTENTIAL INPUTS
Showed significant interest
in new product through
landing page visits
Browsed recipe sites
that use relevant
products
Lives in a geo that experienced
incredibly warm temperatures
3.0 2.0 1.5
9
THE SOLVE…
Develop an MTA with DMP
audience, Adserver log and
DSP log data
Calibrate Model to both
Client vendor MTA and
DSP bid logic
Generate User-level
propensity scores against
audience user-level data
Transform propensity
scores into DSP base bids
Push user-level base bids
into DSP bidding API.
Test lifts and optimize
using DSP Algo
1 2
6 5
3
4
10
VALIDATION METHODOLOGY
11
RESULTS- FASTEST PATH TO CONVERSION,
LOWEST CPA
12
THANK YOU!
Confidential and proprietary. All rights reserved. Distribution without permission is prohibited.

More Related Content

What's hot

Better Advertising Effectiveness Measurement
Better Advertising Effectiveness MeasurementBetter Advertising Effectiveness Measurement
Better Advertising Effectiveness MeasurementMichael Wolfe
 
Real intelligence, measuring marketing performance
Real intelligence, measuring marketing performanceReal intelligence, measuring marketing performance
Real intelligence, measuring marketing performanceNigel Keats
 
Marketing Mix Optimization
Marketing Mix OptimizationMarketing Mix Optimization
Marketing Mix OptimizationPavel Vanecek
 
From multi-channel to cross-channel marketing
From multi-channel to cross-channel marketingFrom multi-channel to cross-channel marketing
From multi-channel to cross-channel marketingForestView
 
Super Charge Your Channel Program
Super Charge Your Channel ProgramSuper Charge Your Channel Program
Super Charge Your Channel ProgramBruce Wirt
 
Newstalk SaaS Bootcamp Day 2
Newstalk SaaS Bootcamp Day 2 Newstalk SaaS Bootcamp Day 2
Newstalk SaaS Bootcamp Day 2 SaaSBootcamp
 
Newstalk SaaS Bootcamp Day 1
Newstalk SaaS Bootcamp Day 1Newstalk SaaS Bootcamp Day 1
Newstalk SaaS Bootcamp Day 1SaaSBootcamp
 
Successful Customer Communications Strategies in 8 Steps and 2 Case Studies
Successful Customer Communications Strategies in 8 Steps and 2 Case StudiesSuccessful Customer Communications Strategies in 8 Steps and 2 Case Studies
Successful Customer Communications Strategies in 8 Steps and 2 Case StudiesVivastream
 
Innovations in marketing effectiveness measurement
Innovations in marketing effectiveness measurement  Innovations in marketing effectiveness measurement
Innovations in marketing effectiveness measurement Michael Wolfe
 
Evaluating Hosted CRM
Evaluating Hosted CRMEvaluating Hosted CRM
Evaluating Hosted CRMDemand Metric
 
CCS Distribution Partner Programs
CCS Distribution Partner ProgramsCCS Distribution Partner Programs
CCS Distribution Partner ProgramsShannon Gronemeyer
 
Profit-Driven Marketing - Digital Summit DC
Profit-Driven Marketing - Digital Summit DCProfit-Driven Marketing - Digital Summit DC
Profit-Driven Marketing - Digital Summit DCAshley Plack
 
Exponential Advertising Audit
Exponential Advertising AuditExponential Advertising Audit
Exponential Advertising Auditlloveday
 
Marketing Campaign Management: PPC
Marketing Campaign Management: PPCMarketing Campaign Management: PPC
Marketing Campaign Management: PPCAdriaan Brits
 
The Perfect Digital Advertising Audit
The Perfect Digital Advertising AuditThe Perfect Digital Advertising Audit
The Perfect Digital Advertising Auditlloveday
 
Quantifying the impact of marketing campaigns on your business using Real Impact
Quantifying the impact of marketing campaigns on your business using Real ImpactQuantifying the impact of marketing campaigns on your business using Real Impact
Quantifying the impact of marketing campaigns on your business using Real ImpactCleverTap
 
Customer experience management - Mapping customer experience across touch-points
Customer experience management - Mapping customer experience across touch-pointsCustomer experience management - Mapping customer experience across touch-points
Customer experience management - Mapping customer experience across touch-pointsGenpact Ltd
 

What's hot (20)

Better Advertising Effectiveness Measurement
Better Advertising Effectiveness MeasurementBetter Advertising Effectiveness Measurement
Better Advertising Effectiveness Measurement
 
Real intelligence, measuring marketing performance
Real intelligence, measuring marketing performanceReal intelligence, measuring marketing performance
Real intelligence, measuring marketing performance
 
Marketing Mix Optimization
Marketing Mix OptimizationMarketing Mix Optimization
Marketing Mix Optimization
 
From multi-channel to cross-channel marketing
From multi-channel to cross-channel marketingFrom multi-channel to cross-channel marketing
From multi-channel to cross-channel marketing
 
Super Charge Your Channel Program
Super Charge Your Channel ProgramSuper Charge Your Channel Program
Super Charge Your Channel Program
 
Newstalk SaaS Bootcamp Day 2
Newstalk SaaS Bootcamp Day 2 Newstalk SaaS Bootcamp Day 2
Newstalk SaaS Bootcamp Day 2
 
Newstalk SaaS Bootcamp Day 1
Newstalk SaaS Bootcamp Day 1Newstalk SaaS Bootcamp Day 1
Newstalk SaaS Bootcamp Day 1
 
Successful Customer Communications Strategies in 8 Steps and 2 Case Studies
Successful Customer Communications Strategies in 8 Steps and 2 Case StudiesSuccessful Customer Communications Strategies in 8 Steps and 2 Case Studies
Successful Customer Communications Strategies in 8 Steps and 2 Case Studies
 
Innovations in marketing effectiveness measurement
Innovations in marketing effectiveness measurement  Innovations in marketing effectiveness measurement
Innovations in marketing effectiveness measurement
 
Evaluating Hosted CRM
Evaluating Hosted CRMEvaluating Hosted CRM
Evaluating Hosted CRM
 
Get Set Go-to-market at a Fast Pace with Field Force Automation Solution
Get Set Go-to-market at a Fast Pace with Field Force Automation SolutionGet Set Go-to-market at a Fast Pace with Field Force Automation Solution
Get Set Go-to-market at a Fast Pace with Field Force Automation Solution
 
The Ultimate Blueprint to Channel Partner Engagement
The Ultimate Blueprint to Channel Partner EngagementThe Ultimate Blueprint to Channel Partner Engagement
The Ultimate Blueprint to Channel Partner Engagement
 
CCS Distribution Partner Programs
CCS Distribution Partner ProgramsCCS Distribution Partner Programs
CCS Distribution Partner Programs
 
Profit-Driven Marketing - Digital Summit DC
Profit-Driven Marketing - Digital Summit DCProfit-Driven Marketing - Digital Summit DC
Profit-Driven Marketing - Digital Summit DC
 
Exponential Advertising Audit
Exponential Advertising AuditExponential Advertising Audit
Exponential Advertising Audit
 
Marketing Campaign Management: PPC
Marketing Campaign Management: PPCMarketing Campaign Management: PPC
Marketing Campaign Management: PPC
 
The Perfect Digital Advertising Audit
The Perfect Digital Advertising AuditThe Perfect Digital Advertising Audit
The Perfect Digital Advertising Audit
 
Market Mix Models: Shining a Light in the Black Box
Market Mix Models: Shining a Light in the Black BoxMarket Mix Models: Shining a Light in the Black Box
Market Mix Models: Shining a Light in the Black Box
 
Quantifying the impact of marketing campaigns on your business using Real Impact
Quantifying the impact of marketing campaigns on your business using Real ImpactQuantifying the impact of marketing campaigns on your business using Real Impact
Quantifying the impact of marketing campaigns on your business using Real Impact
 
Customer experience management - Mapping customer experience across touch-points
Customer experience management - Mapping customer experience across touch-pointsCustomer experience management - Mapping customer experience across touch-points
Customer experience management - Mapping customer experience across touch-points
 

Similar to Attribution Accelerator 2019- MTA Driven Programmatic Bid Optimization

Why is programmatic taking off? What is this revolution all about?
Why is programmatic taking off?  What is this revolution all about?Why is programmatic taking off?  What is this revolution all about?
Why is programmatic taking off? What is this revolution all about?Datacratic
 
The PPC Playbook: Taking Command of Your Campaigns in the Age of AI
The PPC Playbook: Taking Command of Your Campaigns in the Age of AIThe PPC Playbook: Taking Command of Your Campaigns in the Age of AI
The PPC Playbook: Taking Command of Your Campaigns in the Age of AIPinpointe On-Demand
 
Data Science Salon: Enabling self-service predictive analytics at Bidtellect
Data Science Salon: Enabling self-service predictive analytics at BidtellectData Science Salon: Enabling self-service predictive analytics at Bidtellect
Data Science Salon: Enabling self-service predictive analytics at BidtellectFormulatedby
 
The Pros and Cons of PPC Bidding
The Pros and Cons of PPC BiddingThe Pros and Cons of PPC Bidding
The Pros and Cons of PPC BiddingHanapin Marketing
 
nextNY Online Marketing School - SEM Presentation
nextNY Online Marketing School - SEM PresentationnextNY Online Marketing School - SEM Presentation
nextNY Online Marketing School - SEM PresentationnextNY
 
Programmatic buying for everyone
Programmatic buying for everyoneProgrammatic buying for everyone
Programmatic buying for everyoneMcounts
 
programmatic advertising.ppt
programmatic advertising.pptprogrammatic advertising.ppt
programmatic advertising.pptRaviKumar695380
 
Choosing the Right Trading Desk for Your Display Programmatic Buying
Choosing the Right Trading Desk for Your Display Programmatic BuyingChoosing the Right Trading Desk for Your Display Programmatic Buying
Choosing the Right Trading Desk for Your Display Programmatic BuyingAcquisio
 
Digital Ad Tips: Unleash Potential
Digital Ad Tips: Unleash PotentialDigital Ad Tips: Unleash Potential
Digital Ad Tips: Unleash PotentialSEOExp
 
What's an ABM Solution Really Worth? Understanding the Total Economic Impact ...
What's an ABM Solution Really Worth? Understanding the Total Economic Impact ...What's an ABM Solution Really Worth? Understanding the Total Economic Impact ...
What's an ABM Solution Really Worth? Understanding the Total Economic Impact ...Demandbase
 
[Google] Display smart bidding external guide
[Google] Display smart bidding external guide[Google] Display smart bidding external guide
[Google] Display smart bidding external guideDuy, Vo Hoang
 
UNLEASHING THE POWER OF PROGRAMMATIC ADVERTISING
UNLEASHING THE POWER OF PROGRAMMATIC ADVERTISINGUNLEASHING THE POWER OF PROGRAMMATIC ADVERTISING
UNLEASHING THE POWER OF PROGRAMMATIC ADVERTISINGlokeshwarmaha
 
turn_predictivetargeting_factsheet_a4_ff
turn_predictivetargeting_factsheet_a4_ffturn_predictivetargeting_factsheet_a4_ff
turn_predictivetargeting_factsheet_a4_ffAnand Rao Vala
 
B2B Marketing to Millennials: Technology that Meets Expectations 9.8
B2B Marketing to Millennials: Technology that Meets Expectations 9.8B2B Marketing to Millennials: Technology that Meets Expectations 9.8
B2B Marketing to Millennials: Technology that Meets Expectations 9.8IBM Watson Commerce
 
The Business Case for ABM Part 2 with Kwanzoo and Obility
The Business Case for ABM Part 2 with Kwanzoo and ObilityThe Business Case for ABM Part 2 with Kwanzoo and Obility
The Business Case for ABM Part 2 with Kwanzoo and ObilityLiz Mallett
 
AUTOMATION & CROSS-CHANNEL
AUTOMATION & CROSS-CHANNELAUTOMATION & CROSS-CHANNEL
AUTOMATION & CROSS-CHANNELTinuiti
 
Optimizing Your Digital Marketing Campaigns
Optimizing Your Digital Marketing CampaignsOptimizing Your Digital Marketing Campaigns
Optimizing Your Digital Marketing CampaignsIdea to IPO
 
ppt on significance of digital marketing budgeting and controlling cost.pptx
ppt on significance of digital marketing budgeting and controlling cost.pptxppt on significance of digital marketing budgeting and controlling cost.pptx
ppt on significance of digital marketing budgeting and controlling cost.pptxDivyaBalani7
 
Creative that Counts - Beth Sibbring from Tangible Impact at Columbus WAW
Creative that Counts - Beth Sibbring from Tangible Impact at Columbus WAWCreative that Counts - Beth Sibbring from Tangible Impact at Columbus WAW
Creative that Counts - Beth Sibbring from Tangible Impact at Columbus WAWTim Wilson
 

Similar to Attribution Accelerator 2019- MTA Driven Programmatic Bid Optimization (20)

Why is programmatic taking off? What is this revolution all about?
Why is programmatic taking off?  What is this revolution all about?Why is programmatic taking off?  What is this revolution all about?
Why is programmatic taking off? What is this revolution all about?
 
The PPC Playbook: Taking Command of Your Campaigns in the Age of AI
The PPC Playbook: Taking Command of Your Campaigns in the Age of AIThe PPC Playbook: Taking Command of Your Campaigns in the Age of AI
The PPC Playbook: Taking Command of Your Campaigns in the Age of AI
 
Data Science Salon: Enabling self-service predictive analytics at Bidtellect
Data Science Salon: Enabling self-service predictive analytics at BidtellectData Science Salon: Enabling self-service predictive analytics at Bidtellect
Data Science Salon: Enabling self-service predictive analytics at Bidtellect
 
The Pros and Cons of PPC Bidding
The Pros and Cons of PPC BiddingThe Pros and Cons of PPC Bidding
The Pros and Cons of PPC Bidding
 
nextNY Online Marketing School - SEM Presentation
nextNY Online Marketing School - SEM PresentationnextNY Online Marketing School - SEM Presentation
nextNY Online Marketing School - SEM Presentation
 
Programmatic buying for everyone
Programmatic buying for everyoneProgrammatic buying for everyone
Programmatic buying for everyone
 
programmatic advertising.ppt
programmatic advertising.pptprogrammatic advertising.ppt
programmatic advertising.ppt
 
Choosing the Right Trading Desk for Your Display Programmatic Buying
Choosing the Right Trading Desk for Your Display Programmatic BuyingChoosing the Right Trading Desk for Your Display Programmatic Buying
Choosing the Right Trading Desk for Your Display Programmatic Buying
 
Digital Ad Tips: Unleash Potential
Digital Ad Tips: Unleash PotentialDigital Ad Tips: Unleash Potential
Digital Ad Tips: Unleash Potential
 
What's an ABM Solution Really Worth? Understanding the Total Economic Impact ...
What's an ABM Solution Really Worth? Understanding the Total Economic Impact ...What's an ABM Solution Really Worth? Understanding the Total Economic Impact ...
What's an ABM Solution Really Worth? Understanding the Total Economic Impact ...
 
[Google] Display smart bidding external guide
[Google] Display smart bidding external guide[Google] Display smart bidding external guide
[Google] Display smart bidding external guide
 
UNLEASHING THE POWER OF PROGRAMMATIC ADVERTISING
UNLEASHING THE POWER OF PROGRAMMATIC ADVERTISINGUNLEASHING THE POWER OF PROGRAMMATIC ADVERTISING
UNLEASHING THE POWER OF PROGRAMMATIC ADVERTISING
 
turn_predictivetargeting_factsheet_a4_ff
turn_predictivetargeting_factsheet_a4_ffturn_predictivetargeting_factsheet_a4_ff
turn_predictivetargeting_factsheet_a4_ff
 
B2B Marketing to Millennials: Technology that Meets Expectations 9.8
B2B Marketing to Millennials: Technology that Meets Expectations 9.8B2B Marketing to Millennials: Technology that Meets Expectations 9.8
B2B Marketing to Millennials: Technology that Meets Expectations 9.8
 
The Business Case for ABM Part 2 with Kwanzoo and Obility
The Business Case for ABM Part 2 with Kwanzoo and ObilityThe Business Case for ABM Part 2 with Kwanzoo and Obility
The Business Case for ABM Part 2 with Kwanzoo and Obility
 
AUTOMATION & CROSS-CHANNEL
AUTOMATION & CROSS-CHANNELAUTOMATION & CROSS-CHANNEL
AUTOMATION & CROSS-CHANNEL
 
Optimizing Your Digital Marketing Campaigns
Optimizing Your Digital Marketing CampaignsOptimizing Your Digital Marketing Campaigns
Optimizing Your Digital Marketing Campaigns
 
Mastering CRM Analytics
Mastering CRM AnalyticsMastering CRM Analytics
Mastering CRM Analytics
 
ppt on significance of digital marketing budgeting and controlling cost.pptx
ppt on significance of digital marketing budgeting and controlling cost.pptxppt on significance of digital marketing budgeting and controlling cost.pptx
ppt on significance of digital marketing budgeting and controlling cost.pptx
 
Creative that Counts - Beth Sibbring from Tangible Impact at Columbus WAW
Creative that Counts - Beth Sibbring from Tangible Impact at Columbus WAWCreative that Counts - Beth Sibbring from Tangible Impact at Columbus WAW
Creative that Counts - Beth Sibbring from Tangible Impact at Columbus WAW
 

More from Joy Joseph

The Complex Journey to Unified Marketing Analytics
The Complex Journey to Unified Marketing AnalyticsThe Complex Journey to Unified Marketing Analytics
The Complex Journey to Unified Marketing AnalyticsJoy Joseph
 
Iri growth summit_media and promotion effectiveness_v3
Iri growth summit_media and promotion effectiveness_v3Iri growth summit_media and promotion effectiveness_v3
Iri growth summit_media and promotion effectiveness_v3Joy Joseph
 
Marketing mix or attribution journey towards unified marketing analytics
Marketing mix or attribution   journey towards unified marketing analyticsMarketing mix or attribution   journey towards unified marketing analytics
Marketing mix or attribution journey towards unified marketing analyticsJoy Joseph
 
ARF Rethink 2016 - IRI-Atkins Case Segment Marketing Mix
ARF Rethink 2016 - IRI-Atkins Case Segment Marketing MixARF Rethink 2016 - IRI-Atkins Case Segment Marketing Mix
ARF Rethink 2016 - IRI-Atkins Case Segment Marketing MixJoy Joseph
 
220740_iri_hispanic_pov-4-15-15_1
220740_iri_hispanic_pov-4-15-15_1220740_iri_hispanic_pov-4-15-15_1
220740_iri_hispanic_pov-4-15-15_1Joy Joseph
 
Measuring the “carryover” effects of pricing
Measuring the “carryover” effects of pricingMeasuring the “carryover” effects of pricing
Measuring the “carryover” effects of pricingJoy Joseph
 
Iri cpg summit 2010 dynamic price sensitivity measurement
Iri cpg summit 2010  dynamic price sensitivity measurementIri cpg summit 2010  dynamic price sensitivity measurement
Iri cpg summit 2010 dynamic price sensitivity measurementJoy Joseph
 

More from Joy Joseph (7)

The Complex Journey to Unified Marketing Analytics
The Complex Journey to Unified Marketing AnalyticsThe Complex Journey to Unified Marketing Analytics
The Complex Journey to Unified Marketing Analytics
 
Iri growth summit_media and promotion effectiveness_v3
Iri growth summit_media and promotion effectiveness_v3Iri growth summit_media and promotion effectiveness_v3
Iri growth summit_media and promotion effectiveness_v3
 
Marketing mix or attribution journey towards unified marketing analytics
Marketing mix or attribution   journey towards unified marketing analyticsMarketing mix or attribution   journey towards unified marketing analytics
Marketing mix or attribution journey towards unified marketing analytics
 
ARF Rethink 2016 - IRI-Atkins Case Segment Marketing Mix
ARF Rethink 2016 - IRI-Atkins Case Segment Marketing MixARF Rethink 2016 - IRI-Atkins Case Segment Marketing Mix
ARF Rethink 2016 - IRI-Atkins Case Segment Marketing Mix
 
220740_iri_hispanic_pov-4-15-15_1
220740_iri_hispanic_pov-4-15-15_1220740_iri_hispanic_pov-4-15-15_1
220740_iri_hispanic_pov-4-15-15_1
 
Measuring the “carryover” effects of pricing
Measuring the “carryover” effects of pricingMeasuring the “carryover” effects of pricing
Measuring the “carryover” effects of pricing
 
Iri cpg summit 2010 dynamic price sensitivity measurement
Iri cpg summit 2010  dynamic price sensitivity measurementIri cpg summit 2010  dynamic price sensitivity measurement
Iri cpg summit 2010 dynamic price sensitivity measurement
 

Recently uploaded

Beautiful Sapna Vip Call Girls Hauz Khas 9711199012 Call /Whatsapps
Beautiful Sapna Vip  Call Girls Hauz Khas 9711199012 Call /WhatsappsBeautiful Sapna Vip  Call Girls Hauz Khas 9711199012 Call /Whatsapps
Beautiful Sapna Vip Call Girls Hauz Khas 9711199012 Call /Whatsappssapnasaifi408
 
B2 Creative Industry Response Evaluation.docx
B2 Creative Industry Response Evaluation.docxB2 Creative Industry Response Evaluation.docx
B2 Creative Industry Response Evaluation.docxStephen266013
 
Call Girls In Mahipalpur O9654467111 Escorts Service
Call Girls In Mahipalpur O9654467111  Escorts ServiceCall Girls In Mahipalpur O9654467111  Escorts Service
Call Girls In Mahipalpur O9654467111 Escorts ServiceSapana Sha
 
FESE Capital Markets Fact Sheet 2024 Q1.pdf
FESE Capital Markets Fact Sheet 2024 Q1.pdfFESE Capital Markets Fact Sheet 2024 Q1.pdf
FESE Capital Markets Fact Sheet 2024 Q1.pdfMarinCaroMartnezBerg
 
Aminabad Call Girl Agent 9548273370 , Call Girls Service Lucknow
Aminabad Call Girl Agent 9548273370 , Call Girls Service LucknowAminabad Call Girl Agent 9548273370 , Call Girls Service Lucknow
Aminabad Call Girl Agent 9548273370 , Call Girls Service Lucknowmakika9823
 
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...Sapana Sha
 
RA-11058_IRR-COMPRESS Do 198 series of 1998
RA-11058_IRR-COMPRESS Do 198 series of 1998RA-11058_IRR-COMPRESS Do 198 series of 1998
RA-11058_IRR-COMPRESS Do 198 series of 1998YohFuh
 
Delhi Call Girls CP 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls CP 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip CallDelhi Call Girls CP 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls CP 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Callshivangimorya083
 
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Callshivangimorya083
 
代办国外大学文凭《原版美国UCLA文凭证书》加州大学洛杉矶分校毕业证制作成绩单修改
代办国外大学文凭《原版美国UCLA文凭证书》加州大学洛杉矶分校毕业证制作成绩单修改代办国外大学文凭《原版美国UCLA文凭证书》加州大学洛杉矶分校毕业证制作成绩单修改
代办国外大学文凭《原版美国UCLA文凭证书》加州大学洛杉矶分校毕业证制作成绩单修改atducpo
 
{Pooja: 9892124323 } Call Girl in Mumbai | Jas Kaur Rate 4500 Free Hotel Del...
{Pooja:  9892124323 } Call Girl in Mumbai | Jas Kaur Rate 4500 Free Hotel Del...{Pooja:  9892124323 } Call Girl in Mumbai | Jas Kaur Rate 4500 Free Hotel Del...
{Pooja: 9892124323 } Call Girl in Mumbai | Jas Kaur Rate 4500 Free Hotel Del...Pooja Nehwal
 
Building on a FAIRly Strong Foundation to Connect Academic Research to Transl...
Building on a FAIRly Strong Foundation to Connect Academic Research to Transl...Building on a FAIRly Strong Foundation to Connect Academic Research to Transl...
Building on a FAIRly Strong Foundation to Connect Academic Research to Transl...Jack DiGiovanna
 
VIP High Profile Call Girls Amravati Aarushi 8250192130 Independent Escort Se...
VIP High Profile Call Girls Amravati Aarushi 8250192130 Independent Escort Se...VIP High Profile Call Girls Amravati Aarushi 8250192130 Independent Escort Se...
VIP High Profile Call Girls Amravati Aarushi 8250192130 Independent Escort Se...Suhani Kapoor
 
Predicting Employee Churn: A Data-Driven Approach Project Presentation
Predicting Employee Churn: A Data-Driven Approach Project PresentationPredicting Employee Churn: A Data-Driven Approach Project Presentation
Predicting Employee Churn: A Data-Driven Approach Project PresentationBoston Institute of Analytics
 
Best VIP Call Girls Noida Sector 39 Call Me: 8448380779
Best VIP Call Girls Noida Sector 39 Call Me: 8448380779Best VIP Call Girls Noida Sector 39 Call Me: 8448380779
Best VIP Call Girls Noida Sector 39 Call Me: 8448380779Delhi Call girls
 
dokumen.tips_chapter-4-transient-heat-conduction-mehmet-kanoglu.ppt
dokumen.tips_chapter-4-transient-heat-conduction-mehmet-kanoglu.pptdokumen.tips_chapter-4-transient-heat-conduction-mehmet-kanoglu.ppt
dokumen.tips_chapter-4-transient-heat-conduction-mehmet-kanoglu.pptSonatrach
 
Customer Service Analytics - Make Sense of All Your Data.pptx
Customer Service Analytics - Make Sense of All Your Data.pptxCustomer Service Analytics - Make Sense of All Your Data.pptx
Customer Service Analytics - Make Sense of All Your Data.pptxEmmanuel Dauda
 
From idea to production in a day – Leveraging Azure ML and Streamlit to build...
From idea to production in a day – Leveraging Azure ML and Streamlit to build...From idea to production in a day – Leveraging Azure ML and Streamlit to build...
From idea to production in a day – Leveraging Azure ML and Streamlit to build...Florian Roscheck
 

Recently uploaded (20)

Beautiful Sapna Vip Call Girls Hauz Khas 9711199012 Call /Whatsapps
Beautiful Sapna Vip  Call Girls Hauz Khas 9711199012 Call /WhatsappsBeautiful Sapna Vip  Call Girls Hauz Khas 9711199012 Call /Whatsapps
Beautiful Sapna Vip Call Girls Hauz Khas 9711199012 Call /Whatsapps
 
B2 Creative Industry Response Evaluation.docx
B2 Creative Industry Response Evaluation.docxB2 Creative Industry Response Evaluation.docx
B2 Creative Industry Response Evaluation.docx
 
Call Girls In Mahipalpur O9654467111 Escorts Service
Call Girls In Mahipalpur O9654467111  Escorts ServiceCall Girls In Mahipalpur O9654467111  Escorts Service
Call Girls In Mahipalpur O9654467111 Escorts Service
 
FESE Capital Markets Fact Sheet 2024 Q1.pdf
FESE Capital Markets Fact Sheet 2024 Q1.pdfFESE Capital Markets Fact Sheet 2024 Q1.pdf
FESE Capital Markets Fact Sheet 2024 Q1.pdf
 
VIP Call Girls Service Charbagh { Lucknow Call Girls Service 9548273370 } Boo...
VIP Call Girls Service Charbagh { Lucknow Call Girls Service 9548273370 } Boo...VIP Call Girls Service Charbagh { Lucknow Call Girls Service 9548273370 } Boo...
VIP Call Girls Service Charbagh { Lucknow Call Girls Service 9548273370 } Boo...
 
E-Commerce Order PredictionShraddha Kamble.pptx
E-Commerce Order PredictionShraddha Kamble.pptxE-Commerce Order PredictionShraddha Kamble.pptx
E-Commerce Order PredictionShraddha Kamble.pptx
 
Aminabad Call Girl Agent 9548273370 , Call Girls Service Lucknow
Aminabad Call Girl Agent 9548273370 , Call Girls Service LucknowAminabad Call Girl Agent 9548273370 , Call Girls Service Lucknow
Aminabad Call Girl Agent 9548273370 , Call Girls Service Lucknow
 
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...
 
RA-11058_IRR-COMPRESS Do 198 series of 1998
RA-11058_IRR-COMPRESS Do 198 series of 1998RA-11058_IRR-COMPRESS Do 198 series of 1998
RA-11058_IRR-COMPRESS Do 198 series of 1998
 
Delhi Call Girls CP 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls CP 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip CallDelhi Call Girls CP 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls CP 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
 
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call
 
代办国外大学文凭《原版美国UCLA文凭证书》加州大学洛杉矶分校毕业证制作成绩单修改
代办国外大学文凭《原版美国UCLA文凭证书》加州大学洛杉矶分校毕业证制作成绩单修改代办国外大学文凭《原版美国UCLA文凭证书》加州大学洛杉矶分校毕业证制作成绩单修改
代办国外大学文凭《原版美国UCLA文凭证书》加州大学洛杉矶分校毕业证制作成绩单修改
 
{Pooja: 9892124323 } Call Girl in Mumbai | Jas Kaur Rate 4500 Free Hotel Del...
{Pooja:  9892124323 } Call Girl in Mumbai | Jas Kaur Rate 4500 Free Hotel Del...{Pooja:  9892124323 } Call Girl in Mumbai | Jas Kaur Rate 4500 Free Hotel Del...
{Pooja: 9892124323 } Call Girl in Mumbai | Jas Kaur Rate 4500 Free Hotel Del...
 
Building on a FAIRly Strong Foundation to Connect Academic Research to Transl...
Building on a FAIRly Strong Foundation to Connect Academic Research to Transl...Building on a FAIRly Strong Foundation to Connect Academic Research to Transl...
Building on a FAIRly Strong Foundation to Connect Academic Research to Transl...
 
VIP High Profile Call Girls Amravati Aarushi 8250192130 Independent Escort Se...
VIP High Profile Call Girls Amravati Aarushi 8250192130 Independent Escort Se...VIP High Profile Call Girls Amravati Aarushi 8250192130 Independent Escort Se...
VIP High Profile Call Girls Amravati Aarushi 8250192130 Independent Escort Se...
 
Predicting Employee Churn: A Data-Driven Approach Project Presentation
Predicting Employee Churn: A Data-Driven Approach Project PresentationPredicting Employee Churn: A Data-Driven Approach Project Presentation
Predicting Employee Churn: A Data-Driven Approach Project Presentation
 
Best VIP Call Girls Noida Sector 39 Call Me: 8448380779
Best VIP Call Girls Noida Sector 39 Call Me: 8448380779Best VIP Call Girls Noida Sector 39 Call Me: 8448380779
Best VIP Call Girls Noida Sector 39 Call Me: 8448380779
 
dokumen.tips_chapter-4-transient-heat-conduction-mehmet-kanoglu.ppt
dokumen.tips_chapter-4-transient-heat-conduction-mehmet-kanoglu.pptdokumen.tips_chapter-4-transient-heat-conduction-mehmet-kanoglu.ppt
dokumen.tips_chapter-4-transient-heat-conduction-mehmet-kanoglu.ppt
 
Customer Service Analytics - Make Sense of All Your Data.pptx
Customer Service Analytics - Make Sense of All Your Data.pptxCustomer Service Analytics - Make Sense of All Your Data.pptx
Customer Service Analytics - Make Sense of All Your Data.pptx
 
From idea to production in a day – Leveraging Azure ML and Streamlit to build...
From idea to production in a day – Leveraging Azure ML and Streamlit to build...From idea to production in a day – Leveraging Azure ML and Streamlit to build...
From idea to production in a day – Leveraging Azure ML and Streamlit to build...
 

Attribution Accelerator 2019- MTA Driven Programmatic Bid Optimization

  • 1. BRIDGING THE GAP BETWEEN MTA & PROGRAMMATIC BID OPTIMIZATION October 17, 2019 1
  • 2. 2 SPEAKERS JOY JOSEPH Head- Data & Analytic Services GroupM TIM SMITH Senior Director, Business Development The Trade Desk
  • 3. 3 MTA VS. PROGRAMMATIC OPPOSITE BANKS OF THE RIVER? MTA vs. born out of need to better understand the impact each advertising touchpoint has on outcomes- • More holistic measurement and optimization of campaign execution • Rich insights around audience characteristics and their responsiveness across a spectrum of media journeys and creative components • More explanatory than predictive • In-flight course correction of campaign investment strategy- often at no more than a weekly cadence Programmatic bid optimization was born out of the need for high predictive accuracy, and needs to be able to optimize several bidding decisions per second- • Deliver outcomes rather than explain outcomes • High dimensionality- optimize in real-time across multiple bidding decisions per second • Update models in real-time to increase sensitivity to short-term audience propensity shifts
  • 4. 4 DEFINING THE GAP Marketing Objective MTA Programmatic Bid Optimization Drive campaign goals by identifying opportunities to optimize efficiency of addressable marketing spend across channels, journey stages, & audience X Understand the fractional impact of each touchpoint within the journey on conversions X Cross-channel addressable investment strategy & optimization (channels, supply-side platforms/publishers, creative, placements) X Achieve in-channel campaign performance by optimizing real-time spend allocation at an impression level X Determine optimal bids across ad inventory attributes to drive campaign KPIs X Identify the most effective paths to conversion (frequency & sequencing) X Drive reach or target custom audiences with an extremely high level of predictive accuracy to obtain higher returns on their advertising spend X
  • 5. 5 A CRASH COURSE IN PROGRAMMATIC BIDDING ALGOS Bid decisioning algorithms drive a complex process that: • Translate bidding strategy into quantified bid factors • Optimize bid factors using real-time predictions on campaign KPIs • Prioritize across competing internal bids and submit the bid most likely to win For instance, The Trade Desk evaluates 10 Million Impressions per second. For each of these impressions, The Trade Desk uses a unique bid factoring methodology that offer traders advanced optimization capabilities to narrow targeting and pay the right price by using multiple triggers including time of day, device, ad format and recency. Basically, traders input a bidding strategy based on brand goals and the algorithm tests and optimizes it. However, bidding strategies are set at the aggregate audience segment level rather than user-level, resulting in lower specificity in bidding vs. true user-level bid optimization.
  • 6. 6 USER-LEVEL BIDS VS. SEGMENT BIDDING Segment 1 Bid Multiplier = 0.9 Segment 2 Bid Multiplier = 1.1 Segment 3 Segment 3 1.3 1.1 1.2 1.0 1.4
  • 7. 7 WE NEEDED… A real-time user level scoring system to enhance programmatic bid optimization algorithms.
  • 8. CUSTOMER BID SCORING Use log level data to develop and apply scores for each individual prospect to attain maximum expressiveness Browsing Behavior Geography / Temperature Time & DOW Page Visits POTENTIAL INPUTS Showed significant interest in new product through landing page visits Browsed recipe sites that use relevant products Lives in a geo that experienced incredibly warm temperatures 3.0 2.0 1.5
  • 9. 9 THE SOLVE… Develop an MTA with DMP audience, Adserver log and DSP log data Calibrate Model to both Client vendor MTA and DSP bid logic Generate User-level propensity scores against audience user-level data Transform propensity scores into DSP base bids Push user-level base bids into DSP bidding API. Test lifts and optimize using DSP Algo 1 2 6 5 3 4
  • 11. 11 RESULTS- FASTEST PATH TO CONVERSION, LOWEST CPA
  • 13. Confidential and proprietary. All rights reserved. Distribution without permission is prohibited.