machine learning and predictive marketing
TRANSCRIPT
![Page 1: Machine Learning and Predictive Marketing](https://reader033.vdocuments.net/reader033/viewer/2022060603/62969b9210ab0a3b7b710b9c/html5/thumbnails/1.jpg)
1
Machine Learning and Predictive
MarketingReality, Pitfalls & Potential
Claudia PerlichChief Scientist
@claudia_perlich
![Page 2: Machine Learning and Predictive Marketing](https://reader033.vdocuments.net/reader033/viewer/2022060603/62969b9210ab0a3b7b710b9c/html5/thumbnails/2.jpg)
22
Programmatic Advertising
![Page 3: Machine Learning and Predictive Marketing](https://reader033.vdocuments.net/reader033/viewer/2022060603/62969b9210ab0a3b7b710b9c/html5/thumbnails/3.jpg)
33
Work with Brand
300 Million (US) consumer
100 Billion
bid requests per day
AdExchange
Measurement
Conversion
![Page 4: Machine Learning and Predictive Marketing](https://reader033.vdocuments.net/reader033/viewer/2022060603/62969b9210ab0a3b7b710b9c/html5/thumbnails/4.jpg)
44
Machine Learning & Predictive Modeling:
Algorithms that Learn from Data
![Page 5: Machine Learning and Predictive Marketing](https://reader033.vdocuments.net/reader033/viewer/2022060603/62969b9210ab0a3b7b710b9c/html5/thumbnails/5.jpg)
55
Historical Data is the Input for Predictive Modeling
Income Age Buy
123,000 30 Yes
51,100 40 Yes
68,000 55 No
74,000 46 No
23,000 47 Yes
100,000 49 No
![Page 6: Machine Learning and Predictive Marketing](https://reader033.vdocuments.net/reader033/viewer/2022060603/62969b9210ab0a3b7b710b9c/html5/thumbnails/6.jpg)
66
Machine Learning: Who will buy?
Income
Age
No purchase
Insurance50K
45
Logistic Regression
p(Insurance|37,78000) = 0.53
p(+|x)=
β0 = 3.7
β1 = 0.00013
![Page 7: Machine Learning and Predictive Marketing](https://reader033.vdocuments.net/reader033/viewer/2022060603/62969b9210ab0a3b7b710b9c/html5/thumbnails/7.jpg)
77
To whom should we show an Mercedes ad?
![Page 8: Machine Learning and Predictive Marketing](https://reader033.vdocuments.net/reader033/viewer/2022060603/62969b9210ab0a3b7b710b9c/html5/thumbnails/8.jpg)
88
Whatever metric the marketer chooses is what I will
teach the machine to predict …
![Page 9: Machine Learning and Predictive Marketing](https://reader033.vdocuments.net/reader033/viewer/2022060603/62969b9210ab0a3b7b710b9c/html5/thumbnails/9.jpg)
99
Bid on individuals with high predictions by the modelOnly reach audiences that consistently demonstrate interest in your brand.
SC
OR
ING
CO
NN
EC
T
CAMPAIGN PROGRESS
Conversion
++
+
+
No Longer
in Market
XXAdd to
Prospect Pool
and Serve Ad
+
+
-
-
+
+
![Page 10: Machine Learning and Predictive Marketing](https://reader033.vdocuments.net/reader033/viewer/2022060603/62969b9210ab0a3b7b710b9c/html5/thumbnails/10.jpg)
1010
Predict who will click on the ad
![Page 11: Machine Learning and Predictive Marketing](https://reader033.vdocuments.net/reader033/viewer/2022060603/62969b9210ab0a3b7b710b9c/html5/thumbnails/11.jpg)
1111
Predict who will sign up for a test drive
![Page 12: Machine Learning and Predictive Marketing](https://reader033.vdocuments.net/reader033/viewer/2022060603/62969b9210ab0a3b7b710b9c/html5/thumbnails/12.jpg)
1212
Predict who looks up a dealer location
![Page 13: Machine Learning and Predictive Marketing](https://reader033.vdocuments.net/reader033/viewer/2022060603/62969b9210ab0a3b7b710b9c/html5/thumbnails/13.jpg)
1313
Data in Programmatic Advertising ?
Income Age Buy
123,000 30 Yes
51,100 40 Yes
68,000 55 No
74,000 46 No
23,000 47 Yes
100,000 49 No
![Page 14: Machine Learning and Predictive Marketing](https://reader033.vdocuments.net/reader033/viewer/2022060603/62969b9210ab0a3b7b710b9c/html5/thumbnails/14.jpg)
1414
Digital traces of everything: 100 Billion events per day (US)
amazon.com
4/11/16
nytimes.com
2/15/16
50.240.135.41
166. 216.165.92
207.246.152.60
108.49.133.218
38.104.253.134
208.76.113.13
Mlb.com
3/15/16
Etrade.com
4/25/16
mercedes.com
4/10/16
Zip 4
10023-4592
04/15/16
Zip 4
10023-6924
04/20/16
Zip 4
10016-2324
03/10/16
03/14/16
Web App
Phone/Tablet
Desktop
Phone/Tablet
com.mlb.atbat
04/20/16
com.rovio.angry
02/26/16
com.myfitnesspal.android
3/25/16
4/18/16
IDFA
31AB-26FC-
94AE-756B
amazon.com
4/11/16
![Page 15: Machine Learning and Predictive Marketing](https://reader033.vdocuments.net/reader033/viewer/2022060603/62969b9210ab0a3b7b710b9c/html5/thumbnails/15.jpg)
1515
Predict actions to be taken on site base on all else …
amazon.com
4/11/16
nytimes.com
2/15/16
50.240.135.41
166. 216.165.92
207.246.152.60
108.49.133.218
38.104.253.134
208.76.113.13
Mlb.com
3/15/16
Etrade.com
4/25/16
mercedes.com
4/10/16
Zip 4
10023-4592
04/15/16
Zip 4
10023-6924
04/20/16
Zip 4
10016-2324
03/10/16
03/14/16
Web App
Phone/Tablet
Desktop
Phone/Tablet
com.mlb.atbat
04/20/16
com.rovio.angry
02/26/16
com.myfitnesspal.android
3/25/16
4/18/16
IDFA
31AB-26FC-
94AE-756B
amazon.com
4/11/16
![Page 16: Machine Learning and Predictive Marketing](https://reader033.vdocuments.net/reader033/viewer/2022060603/62969b9210ab0a3b7b710b9c/html5/thumbnails/16.jpg)
1616
Predict who will use an app
amazon.com
4/11/16
nytimes.com
2/15/16
50.240.135.41
166. 216.165.92
207.246.152.60
108.49.133.218
38.104.253.134
208.76.113.13
Mlb.com
3/15/16
Etrade.com
4/25/16
mercedes.com
4/10/16
Zip 4
10023-4592
04/15/16
Zip 4
10023-6924
04/20/16
Zip 4
10016-2324
03/10/16
03/14/16
Web App
Phone/Tablet
Desktop
Phone/Tablet
com.mlb.atbat
04/20/16
com.rovio.angry
02/26/16
com.myfitnesspal.android
3/25/16
4/18/16
IDFA
31AB-26FC-
94AE-756B
amazon.com
4/11/16
![Page 17: Machine Learning and Predictive Marketing](https://reader033.vdocuments.net/reader033/viewer/2022060603/62969b9210ab0a3b7b710b9c/html5/thumbnails/17.jpg)
1717
Predict who will go to the dealership
amazon.com
4/11/16
nytimes.com
2/15/16
50.240.135.41
166. 216.165.92
207.246.152.60
108.49.133.218
38.104.253.134
208.76.113.13
Mlb.com
3/15/16
Etrade.com
4/25/16
mercedes.com
4/10/16
Zip 4
10023-4592
04/15/16
Zip 4
10023-6924
04/20/16
Zip 4
10016-2324
03/10/16
03/14/16
Web App
Phone/Tablet
Desktop
Phone/Tablet
com.mlb.atbat
04/20/16
com.rovio.angry
02/26/16
com.myfitnesspal.android
3/25/16
4/18/16
IDFA
31AB-26FC-
94AE-756B
amazon.com
4/11/16
![Page 18: Machine Learning and Predictive Marketing](https://reader033.vdocuments.net/reader033/viewer/2022060603/62969b9210ab0a3b7b710b9c/html5/thumbnails/18.jpg)
1818
Not interested
Brand action
Logistic Regression
p(sv|x)=
β0 = 0.54
β1 = 0.13
…
β10000000 = -0.82
+ …
Machine learning with ‘Big Data’ …
![Page 19: Machine Learning and Predictive Marketing](https://reader033.vdocuments.net/reader033/viewer/2022060603/62969b9210ab0a3b7b710b9c/html5/thumbnails/19.jpg)
1919
URL’s indicating a visit
of Mercedes dealership
![Page 20: Machine Learning and Predictive Marketing](https://reader033.vdocuments.net/reader033/viewer/2022060603/62969b9210ab0a3b7b710b9c/html5/thumbnails/20.jpg)
2020
‘In the market’ signal
![Page 21: Machine Learning and Predictive Marketing](https://reader033.vdocuments.net/reader033/viewer/2022060603/62969b9210ab0a3b7b710b9c/html5/thumbnails/21.jpg)
2121
Real Estate
![Page 22: Machine Learning and Predictive Marketing](https://reader033.vdocuments.net/reader033/viewer/2022060603/62969b9210ab0a3b7b710b9c/html5/thumbnails/22.jpg)
2222
High-end fitness ..
![Page 23: Machine Learning and Predictive Marketing](https://reader033.vdocuments.net/reader033/viewer/2022060603/62969b9210ab0a3b7b710b9c/html5/thumbnails/23.jpg)
2323
TECH-SAVVY FAMILY-ORIENTED
THRIFTY SHOPPERS
• Prepaid Smartphone Shoppers
• Budget Wireless Shoppers
• Holiday Deals Shoppers
• Sweepstakes Enthusiasts
MUSIC FANS
SPORTS FANS
• MLB Fans
• NBA Fans
• Soccer Fans
• NFL Fans
• NCAA Fans
• IT Professionals
• Mac & PC
Shoppers
• Country Music
• Hip Hop
• Streaming Radio
Listeners• Military Families
• Working Parents
• Family Values
Advocates
Insights from models: BMW vs. Audi
CAR & MOTORCYCLE ENTHUSIASTSLUXURY SHOPPER
HEALTH CONSCIOUS
• Luxury Retail Researchers
• High End Camera
• Jewelry & Watch
• Furniture Shoppers
• HDTV Shoppers
• Energy Savers
• Lawn & Garden Enthusiasts
• Nutrition Conscious Eaters
• Heartburn Suffers
• Food Allergies Researchers
HOME DECORATOR
• Motorcycle Enthusiasts
• Aftermarket Accessories
![Page 24: Machine Learning and Predictive Marketing](https://reader033.vdocuments.net/reader033/viewer/2022060603/62969b9210ab0a3b7b710b9c/html5/thumbnails/24.jpg)
24
Pitfalls:
Things we can predict but should not!
![Page 25: Machine Learning and Predictive Marketing](https://reader033.vdocuments.net/reader033/viewer/2022060603/62969b9210ab0a3b7b710b9c/html5/thumbnails/25.jpg)
2525
Good prediction can be harmful in an industry
focused on bad metrics
![Page 26: Machine Learning and Predictive Marketing](https://reader033.vdocuments.net/reader033/viewer/2022060603/62969b9210ab0a3b7b710b9c/html5/thumbnails/26.jpg)
2626
Click Reality
![Page 27: Machine Learning and Predictive Marketing](https://reader033.vdocuments.net/reader033/viewer/2022060603/62969b9210ab0a3b7b710b9c/html5/thumbnails/27.jpg)
2727
Model learned when people click accidentally:
Fumbling in the dark …
![Page 28: Machine Learning and Predictive Marketing](https://reader033.vdocuments.net/reader033/viewer/2022060603/62969b9210ab0a3b7b710b9c/html5/thumbnails/28.jpg)
2828
Bots/ ‘Non-Human traffic’
6%
2011
36%
2015
![Page 29: Machine Learning and Predictive Marketing](https://reader033.vdocuments.net/reader033/viewer/2022060603/62969b9210ab0a3b7b710b9c/html5/thumbnails/29.jpg)
2929
Anything that can be faked will be faked:
bot penetration
![Page 30: Machine Learning and Predictive Marketing](https://reader033.vdocuments.net/reader033/viewer/2022060603/62969b9210ab0a3b7b710b9c/html5/thumbnails/30.jpg)
3030
Viewabilty?
![Page 31: Machine Learning and Predictive Marketing](https://reader033.vdocuments.net/reader033/viewer/2022060603/62969b9210ab0a3b7b710b9c/html5/thumbnails/31.jpg)
31
Potential
Programmatic as the new digital focus
group!
![Page 32: Machine Learning and Predictive Marketing](https://reader033.vdocuments.net/reader033/viewer/2022060603/62969b9210ab0a3b7b710b9c/html5/thumbnails/32.jpg)
3232
amazon.com
4/11/16
nytimes.com
2/15/16
50.240.135.41
166. 216.165.92
207.246.152.60
108.49.133.218 208.76.113.13
Mlb.com
3/15/16
Etrade.com
4/25/16
mercedes.com
4/10/16
Zip 4
10023-4592
04/15/16
Zip 4
10023-6924
04/20/16
Zip 4
10016-2324
03/10/16
03/14/16
Web App
Phone/Tablet
Desktop
Phone/Tablet
com.mlb.atbat
04/20/16
com.rovio.angry
02/26/16
com.myfitnesspal.android
3/25/16
4/18/16
IDFA
31AB-26FC-
94AE-756B
amazon.com
4/11/16
Linking digital and purchase behavior
![Page 33: Machine Learning and Predictive Marketing](https://reader033.vdocuments.net/reader033/viewer/2022060603/62969b9210ab0a3b7b710b9c/html5/thumbnails/33.jpg)
3333
Measuring incremental impact by creative
![Page 34: Machine Learning and Predictive Marketing](https://reader033.vdocuments.net/reader033/viewer/2022060603/62969b9210ab0a3b7b710b9c/html5/thumbnails/34.jpg)
3434
Use Predictive modeling to ‘look under the hood’:
People who go to Fast Food restaurants
Delicious:
![Page 35: Machine Learning and Predictive Marketing](https://reader033.vdocuments.net/reader033/viewer/2022060603/62969b9210ab0a3b7b710b9c/html5/thumbnails/35.jpg)
3535
Use Predictive modeling to ‘look under the hood’:
Gym rats
Self-improvement:
![Page 36: Machine Learning and Predictive Marketing](https://reader033.vdocuments.net/reader033/viewer/2022060603/62969b9210ab0a3b7b710b9c/html5/thumbnails/36.jpg)
3636
Deep view
into
self
improvement
![Page 37: Machine Learning and Predictive Marketing](https://reader033.vdocuments.net/reader033/viewer/2022060603/62969b9210ab0a3b7b710b9c/html5/thumbnails/37.jpg)
3737
I can predict which creative is most effective for YOU!
![Page 38: Machine Learning and Predictive Marketing](https://reader033.vdocuments.net/reader033/viewer/2022060603/62969b9210ab0a3b7b710b9c/html5/thumbnails/38.jpg)
38
@Claudia_Perlich