Detecting Real-Time Financial Fraud with Cloudflow on Kubernetes
0 likes1,917 views
The document discusses the use of Cloudflow, a toolkit for developing and operating distributed streaming applications on Kubernetes, specifically for real-time financial fraud detection. It outlines the data science process, including model development and deployment, and highlights the integration of machine learning for enhanced analysis. The aim is to streamline the collaboration between data science and data engineering to create smarter applications in enterprises.
![@maasg
HTTP
ingress
[schema]
Enrichment
(+features)
Fraud ML
Scoring
Egress
(console)
Transactions](https://image.slidesharecdn.com/cloudflowfrauddetectionwithcloudflowwebinar2-200423135250/85/Detecting-Real-Time-Financial-Fraud-with-Cloudflow-on-Kubernetes-20-320.jpg)
![@maasg
HTTP
ingress
[schema]
Enrichment
(+features)
Fraud ML
Scoring
Egress
(console)
Transactions
py
DT
Model
Persistent
Volume](https://image.slidesharecdn.com/cloudflowfrauddetectionwithcloudflowwebinar2-200423135250/85/Detecting-Real-Time-Financial-Fraud-with-Cloudflow-on-Kubernetes-21-320.jpg)
![@maasg
HTTP
ingress
[schema]
Enrichment
(+features)
Fraud ML
Scoring
Egress
(console)
Transactions
py
DT
Model
Persistent
Volume](https://image.slidesharecdn.com/cloudflowfrauddetectionwithcloudflowwebinar2-200423135250/85/Detecting-Real-Time-Financial-Fraud-with-Cloudflow-on-Kubernetes-22-320.jpg)
![@maasg
HTTP
ingress
[schema]
Enrichment
(+features)
Fraud ML
Scoring
Egress
(console)
Transactions
py
DT
Model
Persistent
Volume](https://image.slidesharecdn.com/cloudflowfrauddetectionwithcloudflowwebinar2-200423135250/85/Detecting-Real-Time-Financial-Fraud-with-Cloudflow-on-Kubernetes-23-320.jpg)
![@maasg
HTTP
ingress
[schema]
Enrichment
(+features)
Fraud ML
Scoring
Egress
(console)
Transactions
py
DT
Model
Persistent
Volume](https://image.slidesharecdn.com/cloudflowfrauddetectionwithcloudflowwebinar2-200423135250/85/Detecting-Real-Time-Financial-Fraud-with-Cloudflow-on-Kubernetes-24-320.jpg)
![@maasg
HTTP
ingress
[schema]
Enrichment
(+features)
Fraud ML
Scoring
Egress
(console)
Transactions
py
DT
Model
Persistent
Volume](https://image.slidesharecdn.com/cloudflowfrauddetectionwithcloudflowwebinar2-200423135250/85/Detecting-Real-Time-Financial-Fraud-with-Cloudflow-on-Kubernetes-25-320.jpg)
![@maasg
HTTP
ingress
[schema]
Enrichment
(+features)
Fraud ML
Scoring
Egress
(console)
Transactions
py
DT
Model
Persistent
Volume](https://image.slidesharecdn.com/cloudflowfrauddetectionwithcloudflowwebinar2-200423135250/85/Detecting-Real-Time-Financial-Fraud-with-Cloudflow-on-Kubernetes-26-320.jpg)
Detecting Real-Time Financial Fraud with Cloudflow on Kubernetes
- 1. Detecting Real-Time Financial Fraud with Cloudflow on Kubernetes Gerard Maas, Principal Engineer at Lightbend.
- 7. ● Intro: Productizing Data Science ● What’s Cloudflow ● Building a Fraud Detection Model ● Running the Model With Cloudflow Agenda
- 8. Cloudflow is a development toolkit that enables you to quickly develop, orchestrate, and operate distributed streaming applications on Kubernetes.
- 9. $dev>
- 10. $> Streamlet API $> Blueprint $> Sandbox $> build tool extensions $> kubectl cloudflow
- 11. Operator
- 12. $> Streamlet API $> Blueprints $> build extensions $> kubectl cloudflow Operator
- 13. Streamlet inlet(s) outlet(s) { Schema } Streamlets Logic{ Schema } { Schema }
- 16. Easily integrate streamlets written in Akka Streams, Spark Structured Streaming, and Flink Merge different input streams Validate record formats, field values Use ML for more sophisticated analysis Compute aggregations (e.g., statistics) Send results downstream Cloudflow API :: Blueprints
- 17. The Data Science Process we’re here Img src: https://randalscottking.com/machine-learning-overview/
- 19. Transactions Fraud Detection Model Data Understanding Data Preparation Data Modelling Validation Deployment Data Cleaning & Enrichment Data Ingestion Result Propagation Model Scoring model
- 20. @maasg HTTP ingress [schema] Enrichment (+features) Fraud ML Scoring Egress (console) Transactions
- 27. External Batch training Embedded Model E.g. SparkML External Batch training External Model Service E.g. TFServing External Batch training Managed Streams E.g. TFjvm
- 28. The Mission of ML in Cloudflow Infuse “AI/ML” or smarter real-time analytics to existing apps ▪ Loan approval, device maintenance, next best offer, recommendation engine Mix domain logic with streaming analytics and model serving ▪ Offer a programming model and runtime that facilitates the creation of new data-driven services Enable the productization of ML in the Enterprise Create a flowing “stream” between Data Science and Data Engineering
- 29. Get started with Cloudflow at cloudflow.io Join our contributor community at: http://github.com/lightbend/cloudflow
- 30. Thank You Gerard Maas Principal Engineer [email protected] @maasg