Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.

Building Scalable Prediction Services in R

9,522 views

Published on

Delivered by Justin Kamerman (Sr. Data Scientist, Socure) at the 2016 New York R Conference on April 8th and 9th at Work-Bench.

Published in: Data & Analytics
  • Be the first to comment

  • Be the first to like this

Building Scalable Prediction Services in R

  1. 1. Scalable Prediction Services with R
  2. 2. #RstatsNYC @Socure • Real-time fraud detection service using social and online data. • Predictive R models. • Latency SLA with customers. • Model versioning. • Zero-downtime updates.
  3. 3. #RstatsNYC @Socure Challenges • R not dev-ops friendly. • Enterprise prediction services a large commitment. • Enterprise prediction services offer limited model types. • Transferability and transparency of models. • Vendor lock-in.
  4. 4. #RstatsNYC @Socure Solution • Embed R models within dev-op friendly middleware. • Management, deployment, integration leverages existing dev-op processes. • Service scaling using established strategies and methods.
  5. 5. #RstatsNYC @Socure <file> gen_20150215.rds saveRDS()
  6. 6. #RstatsNYC @Socure <model> name = generic version = 20150215 <file> gen_20150215.rds readRDS() saveRDS()
  7. 7. #RstatsNYC @Socure Rook http://…./model/20150215 <model> name = generic version = 20150215 name version model 20150215 Model Map <file> gen_20150215.rds readRDS() saveRDS()
  8. 8. #RstatsNYC @Socure Rook http://…./model/20150215 <model> name = generic version = 20150215 name version model 20150215 Model Map predict() <file> gen_20150215.rds readRDS() saveRDS() JSON
  9. 9. #RstatsNYC @Socure POST generic/20150215 Rook Rook Rook Rook fork() ……..
  10. 10. #RstatsNYC @Socure pmml http://…./generic/20150215 org.jpmml.evaluator ModelEvaluatordoPost() Servlet evaluate() unmarshalPMML() pmml.gbm()
  11. 11. #RstatsNYC @Socure ServletServletServletServlet POST generic/20150215 ……..
  12. 12. #RstatsNYC @Socure Virtual Machine Docker Public Repository ECS ElasticBeanStalk R R RR R R
  13. 13. #RstatsNYC @Socure http://…./generic/20150215 ElasticBeanStalk Prediction Service Prediction ServicePrediction Service US-EAST-1A Prediction Service Prediction ServicePrediction Service US-EAST-1A Prediction Service Prediction ServicePrediction Service US-EAST-1A
  14. 14. #RstatsNYC @Socure
  15. 15. #RstatsNYC @Socure
  16. 16. #RstatsNYC @Socure
  17. 17. #RstatsNYC @Socure Conclusions • Rapid deployment of R models in a scalable robust environment. • Directly leverage R models developed by data scientists and analysts. • Apply existing dev-ops processes for testing, monitoring, scaling, alerting of predictive models. • Possible use of PMML to serialize models in future for compliance.
  18. 18. #RstatsNYC @Socure GitHub https://github.com/Socure/moduleR
  19. 19. #RstatsNYC @Socure We’re Hiring http://www.socure.com/hiring Director of Data Science Senior Data Scientist Director of Engineering

×