Productionizing Data Science at Experience
- 1. Productionizing Data Science at A Startup's (ongoing) Journey building Machine Learning Products
- 2. Agenda • Intro • Setting the Scene • Proposed Pipeline • A Look Back
- 3. Who am I? • Matt Mills • Born and raised in Atlanta • BS in Industrial and Systems Engineering 2014, MS in Analytics 2015 • @statmills or www.statmills.com
- 4. Experience's mobile commerce, ticketing, and data solutions empower sports and entertainment leaders to generate new revenue streams, sell more tickets, and make smarter decisions. www.expapp.com/solutions What is Experience?
- 7. Agenda • Intro • Setting the Scene • Proposed Pipeline • A Look Back
- 8. Data Science at the end of 2016 • ~13 Engineers and 1 (me!) Data Scientist
- 9. Data Science at the end of 2016 • ~13 Engineers and 1 (me!) Data Scientist • What happens to my work?
- 10. Data Science at the end of 2016 • ~13 Engineers and 1 (me!) Data Scientist • What happens to my work? Manager / Management Other Departments Partners
- 11. Data Science at the end of 2016 • ~13 Engineers and 1 (me!) Data Scientist • What happens to my work? Manager / Management Other Departments Partners
- 12. Goal for 2017 • Make an Impact on our Customers (Fans) Influence Fan Behavior Manager / Management Other Departments Partners
- 13. Goal for 2017 • Make an Impact on our Customers (Fans) Predictive Model Influence Fan Behavior Manager / Management Other Departments Partners
- 14. Goal for 2017: Continued • Create a process to deploy models into production and use predictions in real time
- 15. Goal for 2017: Continued • Create a process to deploy models into production and use predictions in real time • Some considerations • Minimal use of limited Engineering Resources • Scalable (speed and processing power) • Cheap, like, super cheap (read: Free) • Had to handle data cleansing
- 17. Some Potential Solutions • Build own R/Python Server
- 18. Some Potential Solutions • Build own R/Python Server • Learn Scala/Spark
- 19. Some Potential Solutions • Build own R/Python Server • Learn Scala/Spark • Pay for ML Service
- 20. Some Potential Solutions • Build own R/Python Server • Learn Scala/Spark • Pay for ML Service
- 21. Scaling Experience Data Science with h2o • ML Algorithms written in pure Java • APIs written for R, Python, Scala, Spark • Built for scale • parallel and distributed out of the box • Open Source
- 22. Scaling Experience Data Science with h2o • ML Algorithms written in pure Java • APIs written for R, Python, Scala, Spark • Built for scale • parallel and distributed out of the box • Open Source • Models exportable as Java Objects to embed in other apps • Can embed python pre-processing scripts within the POJO
- 23. Agenda • Intro • Setting the Scene • Proposed Pipeline • A Look Back
- 26. h2o vs scikit-learn Syntax and Process https://github.com/h2oai/h2o-meetups/blob/master/2015_05_14_H2O_Overview/H2O_Overview.pdf
- 29. Experience Predictive Modeling Pipeline 1. App Sends Data 2. Data Cleaning in Python 3. Predictions done in h2o 4. App Gets Prediction input() sys.stdout.flush() {JSON}
- 30. Benefits of Using Open Source Software
- 31. Experience Predictive Modeling Setup
- 32. Model Deployment Code Pulled via Github Terraform to create infrastructure and manage state Served via ECS Dockerize via Dockerfile and stored in ECR Discovery via Consul
- 33. Agenda • Intro • Setting the Scene • Proposed Pipeline • A Look Back
- 34. Pros and Cons of Current Set-Up Pros • Automated process to deploy models into production • Can iterate models with no/limited effort from engineering Cons • Can only use algorithms available to h2o (e.g. no multilevel models, GAMs, Bayesian) • h2o drives Python, why not the other way around?
- 35. Conclusion and Questions 1. Lack of skills and/or support doesn’t have to stop you from putting models into production 2. What’s best for your Data Scientists might not be best for your Engineers and vice-versa
- 36. Conclusion and Questions 1. Lack of skills and/or support doesn’t have to stop you from putting models into production 2. What’s best for your Data Scientists might not be best for your Engineers and vice-versa www.statmills.com ? http://docs.h2o.ai/ https://www.expapp.com/about/#careers