Analytics in Action
3 likes714 views
The document discusses various types of analytics including batch, interactive, real-time, and predictive analytics, outlining their definitions and real-world applications. It emphasizes the need for multiple analytics types in practical use cases, such as fraud detection and performance monitoring. Additionally, it highlights technologies like Hadoop, Spark, and WSO2 Analytics that support these analytics functionalities.
![2
from
e1
=
Transac5onStream
-‐>
e2
=
Transac5onStream[e1.cardNo
==
e2.cardNo]
<3:>
within
5000
select
e1.cardNo,
e1.txnID,
e2[0].txnID,
e2[1].txnID,
e2[2].txnID
insert
into
FraudStream;
Fraud
Detec&on:
Real-‐&me
queries](https://image.slidesharecdn.com/analyticsinaction-150730142308-lva1-app6892/85/Analytics-in-Action-24-320.jpg)
Analytics in Action
- 1. Analy&cs in Ac&on Summer School 2015 Seshika Fernando Technical Lead
- 2. What’s in store o Quick recap of key concepts o Real world applica5ons and demos of o Batch Analy5cs o Interac5ve Analy5cs o Real-‐5me Analy5cs o Predic5ve Analy5cs o Combina5ons of the above o Summary
- 3. Data Science is… “the extrac&on of knowledge from large volumes of data that are structured or unstructured”
- 4. Analy&cs Landscape o Batch Analy5cs Extrac5ng knowledge by processing large amounts of stored data o Interac5ve Analy5cs Extrac5ng knowledge by interac5ng with large amounts of stored data by querying o Real-‐5me Analy5cs Extrac5ng knowledge by processing fast moving data o Predic5ve Analy5cs Extrac5ng knowledge from exis5ng data to determine paGerns and predict future outcomes and trends
- 5. Batch Analy&cs in the Real world o KPI Sta5s5cs o Web applica5on stats monitoring o Network/Service sta5s5cs o Aggrega5ons of sensor data o Solving op5miza5on problems o Urban Planning o Revenue distribu5on analysis
- 6. Batch Analy&cs in Ac&on WSO2 API Manager Sta9s9cs
- 8. Interac&ve Analy&cs in the Real world o Log Analysis o HTTP logs o Audit logs o System logs o Ac5vity Monitoring o Tracing workflows o Detec5ng performance issues o Health data monitoring o Fraud Detec5on o Once a fraud is detected, querying other events that maybe related
- 9. Interac&ve Analy&cs in Ac&on HL7 Toolbox
- 14. Real-‐&me Analy&cs in the Real world o Sports o Real-‐5me analysis of team/player performance o Real-‐5me match analy5cs for fans o Geo-‐spa5al o Traffic Monitoring and alerts o Geo-‐fencing requirements for Transporta5on o Anomaly Detec5on o Fraud Detec5on o Network Intrusion Detec5on o Network/Server health monitoring
- 15. Real-‐&me Analy&cs in Ac&on TFL Traffic Monitoring
- 16. Traffic Monitoring -‐ Architecture
- 17. Predic&ve Analy&cs in the Real world o Next value predic5on o Sales forecasts o Electricity loads o Classifica5on o Product Categoriza5on o Customer Segmenta5on o Anomaly Detec5on o Fraud Detec5on o Preven5ve Maintenance
- 18. Predic&ve Analy&cs in Ac&on Customer Predic9on
- 19. Website Ac&vity Data o Product Downloads o Whitepapers o Webinars o Case Studies o Workshops Random Forest
- 20. Test Dataset Actual Customer 100 Non-‐Customer 12977
- 21. Results Predicted Actual Customer Non-‐Customer Customer 100 90 10 Non-‐Customer 12977 0 12977
- 22. Analy&cs in Real life o Most real life use-‐cases need mul5ple types of analy5cs
- 23. Analy&cs in Ac&on Fraud Detec9on
- 24. 2 from e1 = Transac5onStream -‐> e2 = Transac5onStream[e1.cardNo == e2.cardNo] <3:> within 5000 select e1.cardNo, e1.txnID, e2[0].txnID, e2[1].txnID, e2[2].txnID insert into FraudStream; Fraud Detec&on: Real-‐&me queries
- 26. Fraud Detec&on o Known Fraud Modelling o Real-‐5me Analy5cs o Unknown Fraud Modelling o Predic5ve Analy5cs o Parameters for Fraud detec5on o Batch Analy5cs o Predic5ve Analy5cs o Further Analysis once Fraud is detected o Interac5ve Analy5cs
- 27. Summary o Many flavors of Analy5cs o Batch, Interac5ve, Real-‐5me, Predic5ve o Real life use cases need to u5lize different types of analy5cs o Many Technologies available o Hadoop MapReduce, Spark, Storm, R, WSO2 Analy5cs o WSO2 Analy5cs Plaiorm provides Batch, Interac5ve, Real-‐5me and Predic5ve Analy5cs all in one place
- 28. Contact us !