american express slides, mlconf 2013
DESCRIPTION
TRANSCRIPT
![Page 1: American Express Slides, MLconf 2013](https://reader033.vdocuments.net/reader033/viewer/2022051411/5454e67faf79592b448b45ee/html5/thumbnails/1.jpg)
MLConf, San Francisco, CA November 15, 20131
Recommendations @ American Express
Abhijit Bose, Henry H Yuan and Huiming Qu
Data Science and EngineeringAmerican Express Company
MLConf, San Francisco, CA November 15, 2013
![Page 2: American Express Slides, MLconf 2013](https://reader033.vdocuments.net/reader033/viewer/2022051411/5454e67faf79592b448b45ee/html5/thumbnails/2.jpg)
MLConf, San Francisco, CA November 15, 2013 2MLConf, San Francisco, CA November 15, 2013
American Express Today
![Page 3: American Express Slides, MLconf 2013](https://reader033.vdocuments.net/reader033/viewer/2022051411/5454e67faf79592b448b45ee/html5/thumbnails/3.jpg)
MLConf, San Francisco, CA November 15, 2013 3
Our closed loop gives us direct relationships with millions of buyers and sellers
and a wealth of informationabout buyers and sellers
![Page 4: American Express Slides, MLconf 2013](https://reader033.vdocuments.net/reader033/viewer/2022051411/5454e67faf79592b448b45ee/html5/thumbnails/4.jpg)
MLConf, San Francisco, CA November 15, 2013 4
Trust and security have been the hallmarks of the American Express brand for more than 160 years.
Turning good data into more tailored and targeted commerce does not change our privacy policies and principles.
We know customers need transparency and clear explanations.
We use data to better serve our customers. We do not sell personally identifiable information in any context.
Our products must adhere to the highest standards
![Page 5: American Express Slides, MLconf 2013](https://reader033.vdocuments.net/reader033/viewer/2022051411/5454e67faf79592b448b45ee/html5/thumbnails/5.jpg)
MLConf, San Francisco, CA November 15, 2013 5
Data Scientists @ American ExpressDiverse backgrounds (MS, MBA, PhD):
economics
computer scienceelectrical engineeringphysicsstatisticsmechanical engineering
A mix of American Express talent and alumni Of:
and others
operations research
![Page 6: American Express Slides, MLconf 2013](https://reader033.vdocuments.net/reader033/viewer/2022051411/5454e67faf79592b448b45ee/html5/thumbnails/6.jpg)
MLConf, San Francisco, CA November 15, 2013 6
Recommendation opportunities exist in
many different channels
![Page 7: American Express Slides, MLconf 2013](https://reader033.vdocuments.net/reader033/viewer/2022051411/5454e67faf79592b448b45ee/html5/thumbnails/7.jpg)
MLConf, San Francisco, CA November 15, 2013 7
My Offers Mobile App
![Page 8: American Express Slides, MLconf 2013](https://reader033.vdocuments.net/reader033/viewer/2022051411/5454e67faf79592b448b45ee/html5/thumbnails/8.jpg)
MLConf, San Francisco, CA November 15, 2013 8
https://sync.americanexpress.com/
![Page 9: American Express Slides, MLconf 2013](https://reader033.vdocuments.net/reader033/viewer/2022051411/5454e67faf79592b448b45ee/html5/thumbnails/9.jpg)
MLConf, San Francisco, CA November 15, 2013 9
Website Personalization
![Page 10: American Express Slides, MLconf 2013](https://reader033.vdocuments.net/reader033/viewer/2022051411/5454e67faf79592b448b45ee/html5/thumbnails/10.jpg)
MLConf, San Francisco, CA November 15, 2013 10
Merchant Insight Portal
![Page 11: American Express Slides, MLconf 2013](https://reader033.vdocuments.net/reader033/viewer/2022051411/5454e67faf79592b448b45ee/html5/thumbnails/11.jpg)
MLConf, San Francisco, CA November 15, 2013 11
Merchant Name
Merchant Street Address
Total Amount
Amex card used
Merchant Zip Code
Transaction Timestamp
Transaction ID (useful for history, e.g. returns, tips, etc)
What a Typical Transaction Looks Like
![Page 12: American Express Slides, MLconf 2013](https://reader033.vdocuments.net/reader033/viewer/2022051411/5454e67faf79592b448b45ee/html5/thumbnails/12.jpg)
MLConf, San Francisco, CA November 15, 2013 12
Recommender Apps
Transaction history
Customer profile
Merchant profile
Context
InputChannel
Audience
![Page 13: American Express Slides, MLconf 2013](https://reader033.vdocuments.net/reader033/viewer/2022051411/5454e67faf79592b448b45ee/html5/thumbnails/13.jpg)
MLConf, San Francisco, CA November 15, 2013 13
Collaborative Filtering - Recommend what similar users like explicitly or implicitly.
Content based - Recommend similar items solely based on the content of items.
Hybrid- Combines the above two.
General Approaches
![Page 14: American Express Slides, MLconf 2013](https://reader033.vdocuments.net/reader033/viewer/2022051411/5454e67faf79592b448b45ee/html5/thumbnails/14.jpg)
MLConf, San Francisco, CA November 15, 2013
Find the most relevant merchant offers for our cardmembers, with closed loop data and “real time” context.
Transactional History
LifestyleAttributes
Apr 8, 2023AXP Internal
Input to MyOffers
![Page 15: American Express Slides, MLconf 2013](https://reader033.vdocuments.net/reader033/viewer/2022051411/5454e67faf79592b448b45ee/html5/thumbnails/15.jpg)
MLConf, San Francisco, CA November 15, 2013
BatchHadoop Environment
Contextual Information
Real TimeSolr
Offer Database
Offer Contents
CM ChannelsFulfillment
Synced Card
Merchant Reporting
Pre CalculationExpert Rules
MyOffers Ecosystem
![Page 16: American Express Slides, MLconf 2013](https://reader033.vdocuments.net/reader033/viewer/2022051411/5454e67faf79592b448b45ee/html5/thumbnails/16.jpg)
MLConf, San Francisco, CA November 15, 2013 16
•Agile development for shorter cycle
•Platform and software challenges
•Noisy signals, e.g. taxicabs
•Cold-start issue
•Local vs. Online
Lessons Learnt
![Page 17: American Express Slides, MLconf 2013](https://reader033.vdocuments.net/reader033/viewer/2022051411/5454e67faf79592b448b45ee/html5/thumbnails/17.jpg)
MLConf, San Francisco, CA November 15, 2013 17
Lesson Learnt – Geo-Fencing is Critical
![Page 18: American Express Slides, MLconf 2013](https://reader033.vdocuments.net/reader033/viewer/2022051411/5454e67faf79592b448b45ee/html5/thumbnails/18.jpg)
MLConf, San Francisco, CA November 15, 2013
Current Focus is to build out an end-to-end platform and a rich experimentation layer
•Centralization of data
•Better algorithms
•Better incorporation of customer feedback
18
![Page 19: American Express Slides, MLconf 2013](https://reader033.vdocuments.net/reader033/viewer/2022051411/5454e67faf79592b448b45ee/html5/thumbnails/19.jpg)
MLConf, San Francisco, CA November 15, 2013 19
d3.js
Custom ML Implementations
Technologies
![Page 20: American Express Slides, MLconf 2013](https://reader033.vdocuments.net/reader033/viewer/2022051411/5454e67faf79592b448b45ee/html5/thumbnails/20.jpg)
MLConf, San Francisco, CA November 15, 2013 20
Build the next generation of:-Recommendation systems-Graph Algorithms -Machine Learning algorithms for Marketing, Fraud and a variety of problems-Data products -Experiments
We are Hiring!
![Page 21: American Express Slides, MLconf 2013](https://reader033.vdocuments.net/reader033/viewer/2022051411/5454e67faf79592b448b45ee/html5/thumbnails/21.jpg)
MLConf, San Francisco, CA November 15, 2013 21
Please Contact us at:Abhijit Bose
VP, Data Science & Engineeringhttp://www.linkedin.com/in/abose
Henry YuanDirector, Data Science
http://www.linkedin.com/pub/henry-yuan/4/29b/[email protected]
Huiming QuSr. Data Scientist, Data Science & Engineering
http://www.linkedin.com/pub/huiming-qu/4/400/[email protected]