R as a Service

Using the R programming language as a service can boost productivity and bring powerful benefits to your organisation. Originally Presented at R in Insurance 2016

Transcript

1. msellors@mango-solutions.com R as a Service 11th July 2016 Mark Sellors Head of Mango Data Labs msellors@mango-solutions.com
2. msellors@mango-solutions.com Claim processing is human powered, labour intensive and slow!
3. msellors@mango-solutions.com can help!
4. msellors@mango-solutions.com Old workflow • Claim received • Passed to human processing team • Claim is processed • Result decided • Result conveyed to customer
5. msellors@mango-solutions.com Easy acceptance Easy rejection The tricky middle area Human processing team Claims in How can we optimise?
6. msellors@mango-solutions.com New Workflow • Claim received • Claim form scanned • OCR performed and converted to XML representation • XML file is passed to an R service • Claim is compared against past claims and scored • Score determines next action: • Immediate payout • Immediate refusal • Passed to processing team for further action
7. msellors@mango-solutions.com Workflow • Claim received • Claim form scanned • OCR performed and converted to XML representation • XML file is passed to an R service • Claim is compared against past claims and scored • Score determines next action: • Immediate payout • Immediate refusal • Passed to processing team for further action XML file is passed to an R service
8. msellors@mango-solutions.com Any function you create in R can be turned into a service
9. msellors@mango-solutions.com Corporate Network Website Inputs Results Inputs Results
10. msellors@mango-solutions.com Creating an API in R • RServe • OpenCPU • Plumber • DeployR • Probably others
11. msellors@mango-solutions.com Other Considerations • Utilise big data R packages • Bigmemory, uses C, stores data in memory • ff package, Fast File lookup, not stored in memory • Build single purpose components where possible • Ensure that dataset creation is considered as a crucial aspect of design • Embed into end users workflows, not the other way round
12. msellors@mango-solutions.com > summary(talk) • Deploying R as a service (API) is increasingly straightforward • Quicker, Faster, Stronger • Heavily optimised functions and data flows work best • Put the business challenge before the analytic problem
13. msellors@mango-solutions.com Thanks!