Contenu connexe Similaire à Predictive Analytics - Display Advertising & Credit Card Acquisition Use cases (20) Predictive Analytics - Display Advertising & Credit Card Acquisition Use cases 1. Copyright © 2013. Tiger Analytics
Using Advanced Analytics to bring
Business Value
Two case studies in Digital Advertising
_________________________
Mahesh Kumar
CEO, Tiger Analytics
2. Copyright © 2013. Tiger Analytics
Tiger Analytics
• Boutique consulting firm solving business problems using
advanced data analytics
• Focus areas
– Digital advertising and Social Media
– Marketing and Customer Analytics
– Retail and CPG
– Transportation
• Offices in Bay area, North Carolina, and India
3. Copyright © 2013. Tiger Analytics
• Display Advertising through Real-time bidding (RTB)
– Background on RTB
– Business problem: improve CTR
– Solution Approach and Results
• Credit Card Customer Acquisition via Facebook Ads
– Facebook ads platform
– Business problem: optimal targeting and bidding
– Application to credit card marketing
3
Overview – Two case studies
4. Copyright © 2013. Tiger Analytics
Display Advertising through Real-time
bidding (RTB)
Case Study # 1
5. Copyright © 2013. Tiger Analytics 5
Display Advertising – Real Time Bidding
Milliseconds to bid and load ad …
Waiting for ad
from ad exchange
…
Male,
20-30 yrs, NYC
Tech user
6. Copyright © 2013. Tiger Analytics 6
Display Advertising – Real Time Bidding
Targeted
Ads
7. Copyright © 2013. Tiger Analytics
Real Time Bidding (RTB) for Display Ads
7
Ad-Exchange Ad-network 2
Publisher
(NYT.com)
Tech section
Ad-network 1
Ad-network 3
Advertiser
Advertiser
Advertiser
Male,
20-30 yrs,
New York,
Tech user
• The entire process takes less than 500 milliseconds
• RTB share of online ads is estimated to be $2B per year
8. Copyright © 2013. Tiger Analytics
Business Problem
• Click-through rate (CTR) prediction: Given a campaign line,
what is the predicted CTR for an impression based on
– User characteristics
– Webpage characteristics
• Identify impressions with highest CTR?
8
9. Copyright © 2013. Tiger Analytics
Maximizing the CTR is Critical For Cost Optimization
9
High CTR is good for everyone: users, advertiser, and publisher
High
CTR
Relevant content
for Users
Revenue
maximization for
Publisher
Relevant
audience for
Advertiser
11. Copyright © 2013. Tiger Analytics
Data challenges
• Challenges
– More than 5000 variables
– Hundreds of millions of data points
– Sparse and missing data
– Clicks are very rare (typically 1 click in every 3,000 impressions)
11
12. Copyright © 2013. Tiger Analytics
• Case sampling
– Keep all impressions with clicks
– Keep only a random sample of 1% non-clicks
• This reduced the data size by 100-fold, but prediction
accuracy was as good as when using all data
12
Reducing the number of data sets
13. Copyright © 2013. Tiger Analytics
Logistic Regression results
13
-
50
100
150
200
250
300
350
400
450
1 1001 2001 3001 4001 5001
predicted
baseline
K K K K K K
0% 20% 40% 60% 80% All data
• Top 20% of data got 232 out of 415 (56%) of clicks
• A lift of 180%
16. Copyright © 2013. Tiger Analytics
Credit Card Customer Acquisition
Through Social Media Marketing
Case Study # 2
18. Copyright © 2013. Tiger Analytics
Ads on Facebook
Newsfeed on Desktop Newsfeed on Mobile
Right Hand Side on Desktop
Sponsored Story
Image source:
Facebook
21. Copyright © 2013. Tiger Analytics
Case study: credit card marketing
Cash Back
1,000,000
Impressions
300
Clicks
3
Applications
1
Approval
Conversions are rare events when compared to clicks. The challenge is to be able to make
meaningful inferences based on very little data, especially early on in the campaign.
Click-through rate
0.03%
Conversion rate
1%
Approval rate
33%
22. Copyright © 2013. Tiger Analytics
Micro Segments
1 Segment 50 Segments
50 x 2 =
100 Segments
2 Genders 4 Age Groups
100 x 4 =
400 Segments
25 Interest Clusters
400 x 25 =
10,000 Segments
23. Copyright © 2013. Tiger Analytics
Methodology
• Identify high performance segments
– Statistically significant difference in ctr, cpc, cost per conversion, etc.
– Use ctr as a proxy for conversion rate
• Actions on high performance segments
– Allocate higher budget
– Increase bid price
23
24. Copyright © 2013. Tiger Analytics
Data aggregation
Segment Level Data
(Sparse and Noisy)
Identify Important Dimensions
(Using Statistical Models)
25. Copyright © 2013. Tiger Analytics
Segment performance estimation
Model Estimates
Observed Performance
Prior Knowledge
Inferred Performance
26. Copyright © 2013. Tiger Analytics
Bidding
Brand A
Brand B
Other Competition for Ad Space
Bid: $1.60
Bids
WIN
Bids will differ by Ad and Micro
segment, and will change over
time
27. Copyright © 2013. Tiger Analytics
Budget Allocation
• Increase budget for high
performance segments and reduce
for low performance ones
– Business rules around minimum
and maximum limits
28. Copyright © 2013. Tiger Analytics
Methodology
Segment Level
Observed Data
Inferred Performance Indicators
Based on priors, observed, model estimates
Cost per
Application
Success
Rate
Dynamic Budget Allocation
Based on inferred performance indicators
and business constraints
Historical
Campaign Data
Priorsof
Performance
Indicators
Weighted Data
Click vs. view through, card value, application
result, recency, delay in view-through appls
Cost per
Acquisition
Model Performance
as a function of targeting
dimensions
Model Estimates of
Performance Indicators
Dynamic Bid Allocation
Based on observed/historical
Bid-Spend relationships
Continual monitoring and
analysis
Business
Constraints
29. Copyright © 2013. Tiger Analytics
Results: Increased CTR
29
• Overall increase in CTR by 50% across more than 100 brands
30. Copyright © 2013. Tiger Analytics
Results: Lower costs
30
• Overall decrease in CPA of 25% across more than 100 brands
31. Copyright © 2013. Tiger Analytics
Concluding remarks
• Online and social advertising are fast growing areas with
– Plenty of data
– A large number of interesting problems
• Predictive analytics can add a lot value in this business
– Significant improvement in CTR means better targeted ads
– As much as 25% reduction in cost of media
• Our solutions are being used by several leading startups to
serve billions of ads for Fortune 500 companies
31
32. Copyright © 2013. Tiger Analytics
Questions / Comments ?
mahesh@tigeranalytics.com
www.tigeranalytics.com
32
Notes de l'éditeur CTR is a Not a sole predictor of social media campaign, but from cost perspective, CTR optimizes. CTR best metric for optimization. Facebook alone has 845 Million users, very significant reach and comparable to TV, but it is coupled with interactivity. You can now have a dialogue with customers and build a story around your brand with social. Almost 4 billion pieces of content shared each week