wso2con usa 2015: patterns for deploying analytics in the real world
TRANSCRIPT
Analy2cs Pa#erns
• Batch Analy2cs • Real-‐2me Analy2cs • Interac2ve Analy2cs • Predic2ve Analy2cs • Batch + Real-‐2me • Real-‐2me + Predic2ve • WSO2 Solu2ons Source: data-analytics.github.io
Batch Analy2cs
Genera4ng insight by processing large amounts of stored data
● KPI Statistics ○ Application Statistics Monitoring ○ Network / Service Statistics ○ Sensor Data Aggregation
● Solving Optimization Problems ○ Urban Planning ○ Revenue Distribution Analysis
Source: www.e-deal.com
Real-‐2me Analy2cs
Making sense of fast moving data ● Sports
○ Real-time Analysis of Player Performance ○ Real-time Match Analysis
● Geo-Spatial ○ Traffic Monitoring and Alerting ○ Geo-fencing
● Anomaly Detection ○ Fraud Detection ○ Network Intrusion Detection ○ Server Health Monitoring
Source: www.promojam.com
Interac2ve Analy2cs
Near Real-‐4me Indexed Data Search
● Log Analysis ○ Application / System Logs
● Activity Monitoring ○ Tracking Message Flows
● Fraud Detection ○ Executing queries to lookup related
data in a detected fraud situation ● HL7 Data Exploration
○ ESB HL7 Transport Interfaced with DAS
Source: befoundonline.com
Predic2ve Analy2cs
Analyze Exis4ng Data to Predict Future Events ● Next Value Prediction
○ Sales Forecasts ○ Electricity Loads
● Classification ○ Product Categorization ○ Customer Segmentation
● Anomaly Detection ○ Fraud Detection ○ Preventive Maintenance
Batch + Real-‐2me Analy2cs
Using batch processing results in real-‐4me flows
● Batch Processing done for processing historical data ● Real-time Processing done at the same time for
understanding present snapshot situation ● Overlay summarized historical data with real-time
data to compare current vs past behavior
Source: marketplace.rackspace.com
Batch + Real-‐2me Analy2cs In Ac2on: CEP Event Tables
● WSO2 DAS Analytics Event Tables ○ CEP Event Table extension used to lookup
persisted analytics table data in DAS ○ Used in CEP execution plans to lookup/join/
enrich real-time event streams
Batch + Real-‐2me Analy2cs In Ac2on: No2fica2ons ● WSO2 DAS Spark Event Publish Relation Provider
○ Spark SQL jobs are able to send batch job results as events back to the server as events, to be processed by CEP and send notifications
Real-‐2me + Predic2ve Analy2cs
Using Predic4ve Analy4cs results in real-‐4me flows
● Machine learning models first created ● The ML model is used in real-time execution by
applying the model with parameters extracted from the flow
● Use Case: Unknown Fraud Modelling ● WSO2 CEP meets ML
○ WSO2 CEP StreamProcessor extension for ML provides a way to apply ML models in execution plans
e.g. :- from InputStream#ml:predict('registry:/_system/governance/ml/indian-diabetes-model', 'double') select * insert into PredictionStream;
WSO2 Solu2ons Based on the Analy2cs PlaOorm
● WSO2 Fraud Detection Solution ○ Built for detecting credit card fraud ○ The rules extensible with customized Siddhi
execution plans for any type of fraud detection ○ Currently uses Real-time and Interactive
Analytics features ● WSO2 Log Analytics Solution
○ Distributed indexing and searching of any type of logs stored in the system
○ Notifications support with Real-time event processing features
○ Application / Server health prediction with Machine Learning
○ Uses Interactive + Real-time Analytics + Machine Learning features Source: www.retrospective.centeractive.com
Source: multichannelmerchant.com