Preview 2-690.pptx

Building Data Analytics Pipelines Using Azure Data Factory, HDInsight, Azure ML and More

1.0x

Preview 2-690.pptx

Created 2 years ago

Duration 0:00:00
lesson view count 47
Building Data Analytics Pipelines Using Azure Data Factory, HDInsight, Azure ML and More
Select the file type you wish to download
Slide Content
  1. Mike Flasko

    Slide 1 - Mike Flasko

    • Principal Group Program Manager
    • Building Data Analytics Pipelines using Azure Data Factory, HDInsight, Azure ML and more
    • 2-690
    • //build/ content is being presented by Microsoft Office Mix The video for this session will be available shortly
  2. What & Why?

    Slide 2 - What & Why?

    • Deep Dive: Customer Churn Analysis
    • Common Use Cases
    • Roadmap, Q & A
    • Agenda
  3. Customers are looking to derive more and more value from data…

    Slide 3 - Customers are looking to derive more and more value from data…

    • Agent allocation
    • Usage optimization
    • Operational telemetry
    • Predictive maintenance
    • Supply chain optimization
    • User segmentation
    • Personalized offers
    • Product recommendation
    • Fraud detection
    • Risk management
    • Sales forecasting
    • Demand forecasting
    • Sales lead scoring
    • Predict customer churn
    • EXAMPLES
    • Sales and marketing
    • Finance and risk
    • Customer and channel
    • Operational Excellence
    • Enhanced Customer Service
    • Actuarial modeling
  4. Customers are looking to derive more and more value from data…

    Slide 4 - Customers are looking to derive more and more value from data…

    • Agent allocation
    • Usage optimization
    • Operational telemetry
    • Predictive maintenance
    • Supply chain optimization
    • User segmentation
    • Personalized offers
    • Product recommendation
    • Fraud detection
    • Risk management
    • Sales forecasting
    • Demand forecasting
    • Sales lead scoring
    • Predict customer churn
    • EXAMPLES
    • Sales and marketing
    • Finance and risk
    • Customer and channel
    • Operational Excellence
    • Enhanced Customer Service
    • Actuarial modeling
  5. Slide 6

    • Azure Blob Storage
    • Azure DB
    • Raw Materials
    • Acquire Raw Materials
    • Transform raw materials into “finished goods”
    • Deliver
    • Data Sources
    • Ingest
    • Transform & Analyze
    • Publish
  6. Slide 7

    • Last Name
    • First Name
    • Country
    • Age
    • Flasko
    • Mike
    • Canada
    • 32
    • Anand
    • Subbaraj
    • USA
    • 30
    • Gaurav
    • Malhotra
    • USA
    • 72
    • ….
    • ….
    • ….
    • Last Name
    • First Name
    • At risk of churning
    • ….
    • Flasko
    • Mike
    • Yes
    • Anand
    • Subbaraj
    • No
    • Gaurav
    • Malhotra
    • Yes
    • ….
    • Raw Materials
    • “Finished Good”
    • Predict customer churn
  7. Slide 8

    • Azure Blob Storage
    • Call Log Files
    • Customer Table
    • On Premises
    • Data Mart
    • Call Log Files
    • Customer Table
    • Azure DB
    • Customer Churn Table
    • Visualize
    • Data Set
    • (Collection of files, DB table, etc)
    • Activity: a processing step
    • (Hadoop job, custom code, ML model, etc)
    • Pipeline: a sequence of
    • activities (logical group)
    • Data Factory Concepts
    • Data Sources
    • Ingest
    • Transform & Analyze
    • Publish
    • Customer Call Details
    • Customers Likely to Churn
    • Transform, Combine, etc
    • Analyze
    • Move
  8. Demo: Customer Churn Pipeline

    Slide 9 - Demo: Customer Churn Pipeline

  9. Data Sets: time slicing

    Slide 10 - Data Sets: time slicing

    • Monthly
    • Jan
    • Feb
    • March
    • Data Set 1
    • Monthly
    • Jan
    • Feb
    • March
    • Data Set 2
    • Activity
    • Hourly
    • 1
    • 24
    • Data Set 3
    • Mon
    • Tues
    • Wed
    • Data Set 4
    • Activity
    • Run 1
    • Run 2
    • Run 3
    • Run 1
    • Daily
  10. Azure Data Factory

    Slide 11 - Azure Data Factory

    • A managed cloud service for building & operating data pipelines (aka. data flows)
    • Orchestrate, monitor & schedule
    • compose data processing, storage & movement services (on premises & cloud)
    • Automatic infrastructure mgmt
    • combine pipeline intent w/ resource allocation & mgmt
    • data movement as a service (global footprint & on premises)
    • Single pane of glass
    • one place to manage your network
    • of data flows
  11. Customers are looking to derive more and more value from data…

    Slide 12 - Customers are looking to derive more and more value from data…

    • Agent allocation
    • Usage optimization
    • Operational Telemetry
    • Predictive maintenance
    • Supply chain optimization
    • User segmentation
    • Personalized offers
    • Product recommendation
    • Fraud detection
    • Risk management
    • Sales forecasting
    • Demand forecasting
    • Sales lead scoring
    • Predict customer churn
    • EXAMPLES
    • Sales and marketing
    • Finance and risk
    • Customer and channel
    • Operational Excellence
    • Enhanced Customer Service
    • Actuarial modeling
  12. Additional Common Use Cases: 	  Customer Profiling: 		Product Recommendations, customized offers, etc.  Operational Excellence: 		Telemetry systems, usage optimization, etc

    Slide 13 - Additional Common Use Cases: Customer Profiling: Product Recommendations, customized offers, etc. Operational Excellence: Telemetry systems, usage optimization, etc

  13. Slide 14

    • Added Recently
    • Roadmap
    • Authoring
    • Web-based editor
    • Visual Studio (intellisense & pipeline templates)
    • Application templates (customer churn, recommendations, etc)
    • Data Movement
    • On premises: Oracle DB, file shares
    • Data sources added each month
    • Azure Document Db, Azure Search, Azure SQL DW, Azure Data Lake
    • Data Production
    • Azure Machine Learning
    • HDInsight enhancements
    • Azure Batch
    • Additional Activities
    • Reference Data enhancements
    • Data Management
    • Monitoring diagram: lineage views, custom layout
    • “Recently updated datasets” view
    • Monitoring enhancements: new views, customization, resource utilization views, etc.
    • Enhanced alerting
    • Extensibility
    • Extension SDK -> limited preview
    • Extension SDK release
    • Geo Location
    • Note: can orchestrate/schedule/monitor resources in all geo-regions now
    • Additional geo-regions
  14. Documentation: azure.com/df

    Slide 15 - Documentation: azure.com/df

    • Samples on GitHub
    • Ask questions: MSDN Forum
    • Request & vote on new features
    • Financial services blueprint
    • Case Studies
    • Milliman - Actuarial Automation
    • Rockwell Automation - Operational Excellence
    • Ziosk – Improved Guest Experience & Satisfaction
    • Call to Action
  15. @mflasko

    Slide 16 - @mflasko

    • mike.flasko@microsoft.com
    • Questions ?
  16. Please Complete An Evaluation FormYour input is important!

    Slide 17 - Please Complete An Evaluation FormYour input is important!

    • SAMPLE
    • or
  17. Improve your skills by enrolling in our free cloud development courses at the Microsoft Virtual Academy.

    Slide 18 - Improve your skills by enrolling in our free cloud development courses at the Microsoft Virtual Academy.

    • Try Microsoft Azure for free and deploy your first cloud solution in under 5 minutes!
    • Easily build web and mobile apps for any platform with AzureAppService for free.
    • Resources