SlideShare a Scribd company logo
April 27
GLOBAL AZURE BOOTCAMP IS POWERED BY:
Machine Learning at Hand with Power BI
How Developers and Data Scientists could
Bring AI to the Business User
Thanks to our Sponsors:
Global Sponsor:
Platinum Sponsors:
Gold Sponsors:
Silver Sponsors: Swag Sponsor:
General Sponsor:
About me
• Software Architect @
o 17+ years professional experience
• Microsoft Azure MVP
• External Expert Horizon 2020
• External Expert Eurostars-Eureka, InnoFund Denmark
• Business Interests
o Web Development, SOA, Integration
o IoT, Machine Learning, Computer Intelligence
o Security & Performance Optimization
• Contact
ivelin.andreev@icb.bg
www.linkedin.com/in/ivelin
www.slideshare.net/ivoandreev
AGENDA
The ML Hype
The ML Features in PBI
PBI Premium, Pro, Embedded
Auto ML
Quick Insights
Text Analytics
Key Influencers
Custom R/Python
Demo
“Difference between ML and AI?
- If it is written in Python, probably it is ML.
- If it is written in PowerPoint, probably it is AI.”
* * *
“When you’re fundraising, it’s AI. When you’re hiring, it’s ML.
When you’re implementing, it’s linear regression.“
* * *
“How many data scientists it takes to change a light bulb?
(A data scientist at heart would say “None, as it is a HW problem”)
In fact it is 20 seniors and 1 intern.
Data scientists will argue over a month on the right approach,
the intern will copy the solution from StackOverflow.”
Wondering why AI does not Provide the Expected
Gartner’s Hype Cycle
3. Trough of
disillusionment
4. Slope of
enlightment
5. Plateau of
productivity
Expectations
Time
1. Technology
Launch generates
significant interest
2. A peak of inflated
expectations
“Business impact from AI initiatives takes much longer than
anticipated”
* * *
“Classical ML techniques are extremely
underrated.”
* * *
“…many organizations are pushing to apply deep learning
techniques without even understanding how they apply to their
current initiatives.”
* * *
“Through 2022, over 75% of organizations will
use DNNs for use cases that could be
addressed using classical ML techniques”
Chirag Dekate,
Sr. Research Director
Hype Cycle for Midsize Enterprises, 2018
Users are Drowning in Data
• Environment generates massive data volumes
• Understanding requires AI for exploration
• Users are asking to get insights with no code
The Microsoft Approach
• Place AI in the hands of the end-users
• Expose backend data science work
Microsoft Place AI in the Hands of End-Users
• Azure Cognitive Services
o ML algorithms to extract information from unstructured sources
o Vision, speech and facial recognition, language understanding
• Key Driver Analysis
o Help users understand what combination of impact features determines a KPI
o Automatically point most important factors
• Integrate ML models in PBI
o Azure ML models shared by data scientists to business analysts
• Own ML Models in PBI
o Business Analysts produce own ML models without writing code
o Use Automated ML features targeting users, rather than developers
PBI Target Audience, Licensing and Pricing
• PBI Portfolio
o On-Premises: Desktop, Mobile, Report Server
o Service: Free, Pro, Premium(EM/P SKU), Embedded (A SKU)
• New AI features N/A in Pro
o AI Preview requires A2 SKU but provisioning fails on A2 SKU
o Hint: Create on A4, downscale to A2
• “A” SKUs identical to “EM/P”
o Pro – 8.8 EUR User/ М (Shared)
o A1 SKU – 630 EUR / M (equals EM1)
o A2 SKU – 1’256 EUR / M (equals EM2)
o A3 SKU – 2’518 EUR / M (equals EM3)
o A4 SKU – 5’041 EUR / M (equals P1)
o A5 SKU – 10’087 EUR / M (equals P2)
o A6 SKU – 20’180 EUR / M (equals P3)
PBI
User
Licensing
PBI Free PBI Pro
Capacity
Licensing
P SKU EM SKU A SKU
A SKU EM SKU P SKU
Purchase Azure O365 O365
Sharing
Use Case
Embedded rep. Embedded rep.
SharePoint
MS Teams
Embedded rep.
SharePoint
MS Teams
PBI Apps
Billing Hourly Monthly Monthly
Commitment No Year/Month Year/Month
PBI Service - Pro vs Premium
PRO PREMIUM
Highlights License individual users
• Create content
• Consume content
License capacity to serve multiple users:
• No additional cost to view content
• Creators still need PBI Pro
Size Small-medium deployments (i.e. 200 users) Cost efficient from 500 viewers
Cost Calculator: https://powerbi.microsoft.com/en-us/calculator/
Hardware • Shared capacity=shared resources
• Limitations ensure QoS (1GB file size)
• Dedicated hardware, consistent performance
• Larger data volumes (10GB file size)
Functionality • Dataset refresh - 8 times / 24h • Dataset refresh – 48 times / 24h
• PBI Report Server
• Data flows
• AI workloads
• Embedded deployment
• Sharing, Personalization, Geolocation
Power BI Pro AI Features
• Key Influencers
• Quick Insights
• Cognitive services (manual)
• Python / R script
Power BI Premium AI Features
• AI insights & Cognitive Services
• Automated ML
Automated ML in PBI (Preview)
• Enables Business Analyst to create and train model directly in PBI
• Requires Premium Workspace
• Supports Binary Prediction, Classification and Regression models
• Auto ML Service automatically
o Extracts meaningful parameters from query
o Splits data in training and validation dataset
o Performs training with multiple models
o Summarizes accuracy of model
o Apply model to future data for predictive insights
o AI insights allow direct access to Cognitive services
https://sqlbits.com/Sessions/Event18/Power_BI_Premium_on_a_budget
https://docs.microsoft.com/en-us/power-bi/service-machine-learning-automated
Model Performance Overview
Accuracy Report
Training Details
PBI Desktop Quick Insights
Use insights in Power BI Desktop to explain
increases and decreases seen in visuals
Text Analytics
Use Azure Cognitive Services text analytics
APIs to enrich dataset in PBI M Query
Quick Insights
What is “Quick Insights”:
• Sophisticated ML against dataset and output to formatted visuals
• Output visuals can be integrated in reports
How it works:
o PBI Service: Datasets > … > “Generate Quick Insights”
o PBI Desktop: Data point > right-click > “Analyze”
Key Limitations:
o Not executed against DirectQuery, Streaming and Live connect
o Non-numeric measures are not supported
o Power BI Desktop is limited to the local dataset
Text Analytics in Azure with Power BI
• What is “Text Analytics”:
o Identify meaning and topics from unstructured data
• Limitations:
o Up to 17 languages supported (Apr 2019)
• How it works:
o Register Azure Cognitive Services Text API Key
o M-language query from new Power Query
Text Analytics (Step by Step)
1. Create new query in left queries panel
2. Open View > “Advanced Editor”
3. Write the M-code function query
4. On target query, add function column
5. Set column, func. query and parameter
6. Use column in report (i.e. WordCloud)
➀➁
➂
➃
➄

Key Influencers Visual
Explain the factors that drive a metric of
interest
Top Segments
Explain what combination of factors are
most influential
Key Influencers (preview)
One of the key ML usages is to find hidden insights
What is “Key Influencers”:
• Understand factors that impact a metric of interest
• Understand the importance of each factor
• Top segment factor combinations
Limitations
o Works for categorical & numeric fields
o Not supported for measures and aggregates
o Not supported in PBI Embedded and Mobile
Note: Increasing the number of categories to analyze
means there are fewer observations per category.
The Key Influencers Visual
1. Tabs
o Top contributors / Top segments
2. Metric of interest
3. Restatements
o Help to interpret the pane visuals
4. Average line
o Determined by factors in black
5. Checkbox
o Show only influencers
➀
➁
➂ ➂
➃
➄
The Top Segments Visual
1. Impact of combination of factors on metric
2. Metric of interest
3. Order of segments
o Ranked by % of metric of interest
o Higher proportion ⇨ higher bubble
4. Segment distribution details
o Number of data points ⇨ size of segments
5. Drill down
o Segment details and deep dive
➁
➃
➀
➂
➄
➄
How does Key Influencers Work
Key Influencers
• Runs on ML.NET framework
• Logistic regression to search patterns
• For target category
o Split data points “Category” vs “Not the Category”
o Determine features that distinguish two classes
• Features with little data points are not
considered factors
Top Segments
• Runs on ML.NET framework
• Decision trees to find subgroups
• For each factor
o Decide on best split
o Check representative set reached
• Filters are grouped into segments
Custom AI with Python/R
PBI models with custom and
R/Python visuals
Custom AI with Python/R
• PBI Visuals & Power Query with Python since Feb 2019 (preview Aug 2018)
• PBI Desktop automatically detects runtimes
o Install: https://www.python.org/downloads/, https://www.rstudio.com/
o Packages: pip install [name]; install.packages(‘[name]', dependencies = TRUE)
• Very good for interactive reports trained from past data
• Key Limitations
o 150’000 rows, 250MB, 2MB image, 1 GB RAM
o 60s (Service) / 300s (Desktop)
o PBI Service: limited packages; Python 2.7 and 3.7
• Python IDEs (write and debug Python script)
o Jupyter NB? ML Workbench? VS2019 Python Support
PBI Prediction with Custom Model
https://towardsdatascience.com/how-to-predict-values-from-a-custom-r-model-in-power-bi-3364f83b0015
* Publish to web is currently
not supported for R visuals
(April 2019)
Takeaways & References
• About Automated Machine Learning
o https://docs.microsoft.com/en-us/azure/machine-learning/service/concept-automated-ml
• Power BI Guided Learning
o https://docs.microsoft.com/en-us/power-bi/guided-learning/
• Azure Data-AI-IoT (Samples, Training & Tutorials)
o https://github.com/Azure/data-ai-iot
• PBI for Data Science
o https://www.pbiusergroup.com/communities/community-
home?CommunityKey=5b43099c-d801-49ed-af87-f1da8311f41e
• PBI Samples
o https://docs.microsoft.com/en-us/power-bi/sample-datasets
• Starter Books
Microsoft Power BI ServiceMicrosoft Power BI Desktop
Thanks to our Sponsors:
Global Sponsor:
Platinum Sponsors:
Gold Sponsors:
Silver Sponsors: Swag Sponsor:
General Sponsor:

More Related Content

What's hot

Power bi introduction
Power bi introductionPower bi introduction
Power bi introduction
Bishwadeb Dey
 
ML with Power BI for Business and Pros
ML with Power BI for Business and ProsML with Power BI for Business and Pros
ML with Power BI for Business and Pros
Ivo Andreev
 
Power bi
Power biPower bi
Power bi
jainema23
 
Data analytics and powerbi intro
Data analytics and powerbi introData analytics and powerbi intro
Data analytics and powerbi intro
Berkovich Consulting
 
Power Up with Power BI
Power Up with Power BIPower Up with Power BI
Power Up with Power BI
Michael Hammons
 
Azure Synapse Analytics Overview (r1)
Azure Synapse Analytics Overview (r1)Azure Synapse Analytics Overview (r1)
Azure Synapse Analytics Overview (r1)
James Serra
 
Learn Power BI with Power Pivot, Power Query, Power View, Power Map and Q&A
Learn Power BI with Power Pivot, Power Query, Power View, Power Map and Q&ALearn Power BI with Power Pivot, Power Query, Power View, Power Map and Q&A
Learn Power BI with Power Pivot, Power Query, Power View, Power Map and Q&A
Vishal Pawar
 
Achieving Business Transformation with UiPath RPA
Achieving Business Transformation with UiPath RPAAchieving Business Transformation with UiPath RPA
Achieving Business Transformation with UiPath RPA
Celonis
 
Power platform power automate in a day
Power platform   power automate in a dayPower platform   power automate in a day
Power platform power automate in a day
Narapat Patcharapornpun
 
Intelligent automation with Microsoft Power Automate
Intelligent automation with Microsoft Power AutomateIntelligent automation with Microsoft Power Automate
Intelligent automation with Microsoft Power Automate
Daniel Laskewitz
 
UiPath Summer School Session1
UiPath Summer School Session1 UiPath Summer School Session1
UiPath Summer School Session1
Cristina Vidu
 
The Death of the Star Schema
The Death of the Star SchemaThe Death of the Star Schema
The Death of the Star Schema
DATAVERSITY
 
Modernizing Integration with Data Virtualization
Modernizing Integration with Data VirtualizationModernizing Integration with Data Virtualization
Modernizing Integration with Data Virtualization
Denodo
 
Microsoft Power BI Technical Overview
Microsoft Power BI Technical OverviewMicrosoft Power BI Technical Overview
Microsoft Power BI Technical Overview
David J Rosenthal
 
Power BI Tutorial For Beginners | Power BI Tutorial | Power BI Demo | Power B...
Power BI Tutorial For Beginners | Power BI Tutorial | Power BI Demo | Power B...Power BI Tutorial For Beginners | Power BI Tutorial | Power BI Demo | Power B...
Power BI Tutorial For Beginners | Power BI Tutorial | Power BI Demo | Power B...
Edureka!
 
Power Automate
Power AutomatePower Automate
Power Automate
Fausto Capellan Jr
 
Robotic process automation
Robotic process automationRobotic process automation
Robotic process automation
Bharadwaj Choudhury
 
adb.pdf
adb.pdfadb.pdf
Microsoft Power BI
Microsoft Power BIMicrosoft Power BI
Microsoft Power BI
Geetika
 

What's hot (20)

Power bi introduction
Power bi introductionPower bi introduction
Power bi introduction
 
ML with Power BI for Business and Pros
ML with Power BI for Business and ProsML with Power BI for Business and Pros
ML with Power BI for Business and Pros
 
Power bi
Power biPower bi
Power bi
 
Business intelligence kpi
Business intelligence kpiBusiness intelligence kpi
Business intelligence kpi
 
Data analytics and powerbi intro
Data analytics and powerbi introData analytics and powerbi intro
Data analytics and powerbi intro
 
Power Up with Power BI
Power Up with Power BIPower Up with Power BI
Power Up with Power BI
 
Azure Synapse Analytics Overview (r1)
Azure Synapse Analytics Overview (r1)Azure Synapse Analytics Overview (r1)
Azure Synapse Analytics Overview (r1)
 
Learn Power BI with Power Pivot, Power Query, Power View, Power Map and Q&A
Learn Power BI with Power Pivot, Power Query, Power View, Power Map and Q&ALearn Power BI with Power Pivot, Power Query, Power View, Power Map and Q&A
Learn Power BI with Power Pivot, Power Query, Power View, Power Map and Q&A
 
Achieving Business Transformation with UiPath RPA
Achieving Business Transformation with UiPath RPAAchieving Business Transformation with UiPath RPA
Achieving Business Transformation with UiPath RPA
 
Power platform power automate in a day
Power platform   power automate in a dayPower platform   power automate in a day
Power platform power automate in a day
 
Intelligent automation with Microsoft Power Automate
Intelligent automation with Microsoft Power AutomateIntelligent automation with Microsoft Power Automate
Intelligent automation with Microsoft Power Automate
 
UiPath Summer School Session1
UiPath Summer School Session1 UiPath Summer School Session1
UiPath Summer School Session1
 
The Death of the Star Schema
The Death of the Star SchemaThe Death of the Star Schema
The Death of the Star Schema
 
Modernizing Integration with Data Virtualization
Modernizing Integration with Data VirtualizationModernizing Integration with Data Virtualization
Modernizing Integration with Data Virtualization
 
Microsoft Power BI Technical Overview
Microsoft Power BI Technical OverviewMicrosoft Power BI Technical Overview
Microsoft Power BI Technical Overview
 
Power BI Tutorial For Beginners | Power BI Tutorial | Power BI Demo | Power B...
Power BI Tutorial For Beginners | Power BI Tutorial | Power BI Demo | Power B...Power BI Tutorial For Beginners | Power BI Tutorial | Power BI Demo | Power B...
Power BI Tutorial For Beginners | Power BI Tutorial | Power BI Demo | Power B...
 
Power Automate
Power AutomatePower Automate
Power Automate
 
Robotic process automation
Robotic process automationRobotic process automation
Robotic process automation
 
adb.pdf
adb.pdfadb.pdf
adb.pdf
 
Microsoft Power BI
Microsoft Power BIMicrosoft Power BI
Microsoft Power BI
 

Similar to Machine Learning at Hand with Power BI

GPPB Natural Language PowerBI
GPPB Natural Language PowerBIGPPB Natural Language PowerBI
GPPB Natural Language PowerBI
Samik Roy
 
All you must know about Power BI!.
All you must know about Power BI!.All you must know about Power BI!.
All you must know about Power BI!.
TechSoup
 
All you must know about Power BI!
All you must know about Power BI!All you must know about Power BI!
All you must know about Power BI!
ArethaSimons
 
Power BI Create lightning fast dashboard with power bi & Its Components
Power BI Create lightning fast dashboard with power bi & Its Components Power BI Create lightning fast dashboard with power bi & Its Components
Power BI Create lightning fast dashboard with power bi & Its Components
Vishal Pawar
 
SqlSaturday#699 Power BI - Create a dashboard from zero to hero
SqlSaturday#699 Power BI - Create a dashboard from zero to heroSqlSaturday#699 Power BI - Create a dashboard from zero to hero
SqlSaturday#699 Power BI - Create a dashboard from zero to hero
Vishal Pawar
 
Top 60 Power BI Interview Questions and Answers for 2023.pdf
Top 60 Power BI Interview Questions and Answers for 2023.pdfTop 60 Power BI Interview Questions and Answers for 2023.pdf
Top 60 Power BI Interview Questions and Answers for 2023.pdf
Datacademy.ai
 
Microsoft ignite 2019 highlights
Microsoft ignite 2019 highlightsMicrosoft ignite 2019 highlights
Microsoft ignite 2019 highlights
Anupam Ranku
 
Power BI vs Tableau - An Overview from EPC Group.pptx
Power BI vs Tableau - An Overview from EPC Group.pptxPower BI vs Tableau - An Overview from EPC Group.pptx
Power BI vs Tableau - An Overview from EPC Group.pptx
EPC Group
 
Learn How to Use Microsoft Power BI for Office 365 to Analyze Salesforce Data
Learn How to Use Microsoft Power BI for Office 365 to Analyze Salesforce DataLearn How to Use Microsoft Power BI for Office 365 to Analyze Salesforce Data
Learn How to Use Microsoft Power BI for Office 365 to Analyze Salesforce Data
Netwoven Inc.
 
June2019 release
June2019 releaseJune2019 release
June2019 release
Berkovich Consulting
 
Groupby -Power bi dashboard in hour by vishal pawar-Presentation
Groupby -Power bi dashboard in hour by vishal pawar-Presentation Groupby -Power bi dashboard in hour by vishal pawar-Presentation
Groupby -Power bi dashboard in hour by vishal pawar-Presentation
Vishal Pawar
 
Maintainable Machine Learning Products
Maintainable Machine Learning ProductsMaintainable Machine Learning Products
Maintainable Machine Learning Products
Andrew Musselman
 
20220205 Getting started with power bi
20220205 Getting started with power bi20220205 Getting started with power bi
20220205 Getting started with power bi
Aroh Shukla
 
At the Tipping Point: Considerations for Cloud BI in a Multi-platform BI Ente...
At the Tipping Point: Considerations for Cloud BI in a Multi-platform BI Ente...At the Tipping Point: Considerations for Cloud BI in a Multi-platform BI Ente...
At the Tipping Point: Considerations for Cloud BI in a Multi-platform BI Ente...
Inside Analysis
 
OUGN 2018 - Chatbot and the need to integrate
OUGN 2018 - Chatbot and the need to integrateOUGN 2018 - Chatbot and the need to integrate
OUGN 2018 - Chatbot and the need to integrate
Jon Petter Hjulstad
 
Otbi overview ow13
Otbi overview ow13Otbi overview ow13
Otbi overview ow13
Syaifuddin Ismail
 
Microsoft power bi vs tibco spotfire
Microsoft power bi vs tibco spotfireMicrosoft power bi vs tibco spotfire
Microsoft power bi vs tibco spotfire
Anirudh Kanneganti
 
Business Intelligence in SharePoint 2013
Business Intelligence in SharePoint 2013Business Intelligence in SharePoint 2013
Business Intelligence in SharePoint 2013
Jason Himmelstein
 
SharePoint Inspired 'Get more from your data with Office 365'
SharePoint Inspired 'Get more from your data with Office 365'SharePoint Inspired 'Get more from your data with Office 365'
SharePoint Inspired 'Get more from your data with Office 365'
Xylos
 
Power BI: From the Basics
Power BI: From the BasicsPower BI: From the Basics
Power BI: From the Basics
Nikkia Carter
 

Similar to Machine Learning at Hand with Power BI (20)

GPPB Natural Language PowerBI
GPPB Natural Language PowerBIGPPB Natural Language PowerBI
GPPB Natural Language PowerBI
 
All you must know about Power BI!.
All you must know about Power BI!.All you must know about Power BI!.
All you must know about Power BI!.
 
All you must know about Power BI!
All you must know about Power BI!All you must know about Power BI!
All you must know about Power BI!
 
Power BI Create lightning fast dashboard with power bi & Its Components
Power BI Create lightning fast dashboard with power bi & Its Components Power BI Create lightning fast dashboard with power bi & Its Components
Power BI Create lightning fast dashboard with power bi & Its Components
 
SqlSaturday#699 Power BI - Create a dashboard from zero to hero
SqlSaturday#699 Power BI - Create a dashboard from zero to heroSqlSaturday#699 Power BI - Create a dashboard from zero to hero
SqlSaturday#699 Power BI - Create a dashboard from zero to hero
 
Top 60 Power BI Interview Questions and Answers for 2023.pdf
Top 60 Power BI Interview Questions and Answers for 2023.pdfTop 60 Power BI Interview Questions and Answers for 2023.pdf
Top 60 Power BI Interview Questions and Answers for 2023.pdf
 
Microsoft ignite 2019 highlights
Microsoft ignite 2019 highlightsMicrosoft ignite 2019 highlights
Microsoft ignite 2019 highlights
 
Power BI vs Tableau - An Overview from EPC Group.pptx
Power BI vs Tableau - An Overview from EPC Group.pptxPower BI vs Tableau - An Overview from EPC Group.pptx
Power BI vs Tableau - An Overview from EPC Group.pptx
 
Learn How to Use Microsoft Power BI for Office 365 to Analyze Salesforce Data
Learn How to Use Microsoft Power BI for Office 365 to Analyze Salesforce DataLearn How to Use Microsoft Power BI for Office 365 to Analyze Salesforce Data
Learn How to Use Microsoft Power BI for Office 365 to Analyze Salesforce Data
 
June2019 release
June2019 releaseJune2019 release
June2019 release
 
Groupby -Power bi dashboard in hour by vishal pawar-Presentation
Groupby -Power bi dashboard in hour by vishal pawar-Presentation Groupby -Power bi dashboard in hour by vishal pawar-Presentation
Groupby -Power bi dashboard in hour by vishal pawar-Presentation
 
Maintainable Machine Learning Products
Maintainable Machine Learning ProductsMaintainable Machine Learning Products
Maintainable Machine Learning Products
 
20220205 Getting started with power bi
20220205 Getting started with power bi20220205 Getting started with power bi
20220205 Getting started with power bi
 
At the Tipping Point: Considerations for Cloud BI in a Multi-platform BI Ente...
At the Tipping Point: Considerations for Cloud BI in a Multi-platform BI Ente...At the Tipping Point: Considerations for Cloud BI in a Multi-platform BI Ente...
At the Tipping Point: Considerations for Cloud BI in a Multi-platform BI Ente...
 
OUGN 2018 - Chatbot and the need to integrate
OUGN 2018 - Chatbot and the need to integrateOUGN 2018 - Chatbot and the need to integrate
OUGN 2018 - Chatbot and the need to integrate
 
Otbi overview ow13
Otbi overview ow13Otbi overview ow13
Otbi overview ow13
 
Microsoft power bi vs tibco spotfire
Microsoft power bi vs tibco spotfireMicrosoft power bi vs tibco spotfire
Microsoft power bi vs tibco spotfire
 
Business Intelligence in SharePoint 2013
Business Intelligence in SharePoint 2013Business Intelligence in SharePoint 2013
Business Intelligence in SharePoint 2013
 
SharePoint Inspired 'Get more from your data with Office 365'
SharePoint Inspired 'Get more from your data with Office 365'SharePoint Inspired 'Get more from your data with Office 365'
SharePoint Inspired 'Get more from your data with Office 365'
 
Power BI: From the Basics
Power BI: From the BasicsPower BI: From the Basics
Power BI: From the Basics
 

More from Ivo Andreev

Cybersecurity and Generative AI - for Good and Bad vol.2
Cybersecurity and Generative AI - for Good and Bad vol.2Cybersecurity and Generative AI - for Good and Bad vol.2
Cybersecurity and Generative AI - for Good and Bad vol.2
Ivo Andreev
 
Architecting AI Solutions in Azure for Business
Architecting AI Solutions in Azure for BusinessArchitecting AI Solutions in Azure for Business
Architecting AI Solutions in Azure for Business
Ivo Andreev
 
Cybersecurity Challenges with Generative AI - for Good and Bad
Cybersecurity Challenges with Generative AI - for Good and BadCybersecurity Challenges with Generative AI - for Good and Bad
Cybersecurity Challenges with Generative AI - for Good and Bad
Ivo Andreev
 
JS-Experts - Cybersecurity for Generative AI
JS-Experts - Cybersecurity for Generative AIJS-Experts - Cybersecurity for Generative AI
JS-Experts - Cybersecurity for Generative AI
Ivo Andreev
 
How do OpenAI GPT Models Work - Misconceptions and Tips for Developers
How do OpenAI GPT Models Work - Misconceptions and Tips for DevelopersHow do OpenAI GPT Models Work - Misconceptions and Tips for Developers
How do OpenAI GPT Models Work - Misconceptions and Tips for Developers
Ivo Andreev
 
OpenAI GPT in Depth - Questions and Misconceptions
OpenAI GPT in Depth - Questions and MisconceptionsOpenAI GPT in Depth - Questions and Misconceptions
OpenAI GPT in Depth - Questions and Misconceptions
Ivo Andreev
 
Cutting Edge Computer Vision for Everyone
Cutting Edge Computer Vision for EveryoneCutting Edge Computer Vision for Everyone
Cutting Edge Computer Vision for Everyone
Ivo Andreev
 
Collecting and Analysing Spaceborn Data
Collecting and Analysing Spaceborn DataCollecting and Analysing Spaceborn Data
Collecting and Analysing Spaceborn Data
Ivo Andreev
 
Collecting and Analysing Satellite Data with Azure Orbital
Collecting and Analysing Satellite Data with Azure OrbitalCollecting and Analysing Satellite Data with Azure Orbital
Collecting and Analysing Satellite Data with Azure Orbital
Ivo Andreev
 
Language Studio and Custom Models
Language Studio and Custom ModelsLanguage Studio and Custom Models
Language Studio and Custom Models
Ivo Andreev
 
CosmosDB for IoT Scenarios
CosmosDB for IoT ScenariosCosmosDB for IoT Scenarios
CosmosDB for IoT Scenarios
Ivo Andreev
 
Forecasting time series powerful and simple
Forecasting time series powerful and simpleForecasting time series powerful and simple
Forecasting time series powerful and simple
Ivo Andreev
 
Constrained Optimization with Genetic Algorithms and Project Bonsai
Constrained Optimization with Genetic Algorithms and Project BonsaiConstrained Optimization with Genetic Algorithms and Project Bonsai
Constrained Optimization with Genetic Algorithms and Project Bonsai
Ivo Andreev
 
Azure security guidelines for developers
Azure security guidelines for developers Azure security guidelines for developers
Azure security guidelines for developers
Ivo Andreev
 
Autonomous Machines with Project Bonsai
Autonomous Machines with Project BonsaiAutonomous Machines with Project Bonsai
Autonomous Machines with Project Bonsai
Ivo Andreev
 
Global azure virtual 2021 - Azure Lighthouse
Global azure virtual 2021 - Azure LighthouseGlobal azure virtual 2021 - Azure Lighthouse
Global azure virtual 2021 - Azure Lighthouse
Ivo Andreev
 
Flux QL - Nexgen Management of Time Series Inspired by JS
Flux QL - Nexgen Management of Time Series Inspired by JSFlux QL - Nexgen Management of Time Series Inspired by JS
Flux QL - Nexgen Management of Time Series Inspired by JS
Ivo Andreev
 
Azure architecture design patterns - proven solutions to common challenges
Azure architecture design patterns - proven solutions to common challengesAzure architecture design patterns - proven solutions to common challenges
Azure architecture design patterns - proven solutions to common challenges
Ivo Andreev
 
Industrial IoT on Azure
Industrial IoT on AzureIndustrial IoT on Azure
Industrial IoT on Azure
Ivo Andreev
 
The Power of Auto ML and How Does it Work
The Power of Auto ML and How Does it WorkThe Power of Auto ML and How Does it Work
The Power of Auto ML and How Does it Work
Ivo Andreev
 

More from Ivo Andreev (20)

Cybersecurity and Generative AI - for Good and Bad vol.2
Cybersecurity and Generative AI - for Good and Bad vol.2Cybersecurity and Generative AI - for Good and Bad vol.2
Cybersecurity and Generative AI - for Good and Bad vol.2
 
Architecting AI Solutions in Azure for Business
Architecting AI Solutions in Azure for BusinessArchitecting AI Solutions in Azure for Business
Architecting AI Solutions in Azure for Business
 
Cybersecurity Challenges with Generative AI - for Good and Bad
Cybersecurity Challenges with Generative AI - for Good and BadCybersecurity Challenges with Generative AI - for Good and Bad
Cybersecurity Challenges with Generative AI - for Good and Bad
 
JS-Experts - Cybersecurity for Generative AI
JS-Experts - Cybersecurity for Generative AIJS-Experts - Cybersecurity for Generative AI
JS-Experts - Cybersecurity for Generative AI
 
How do OpenAI GPT Models Work - Misconceptions and Tips for Developers
How do OpenAI GPT Models Work - Misconceptions and Tips for DevelopersHow do OpenAI GPT Models Work - Misconceptions and Tips for Developers
How do OpenAI GPT Models Work - Misconceptions and Tips for Developers
 
OpenAI GPT in Depth - Questions and Misconceptions
OpenAI GPT in Depth - Questions and MisconceptionsOpenAI GPT in Depth - Questions and Misconceptions
OpenAI GPT in Depth - Questions and Misconceptions
 
Cutting Edge Computer Vision for Everyone
Cutting Edge Computer Vision for EveryoneCutting Edge Computer Vision for Everyone
Cutting Edge Computer Vision for Everyone
 
Collecting and Analysing Spaceborn Data
Collecting and Analysing Spaceborn DataCollecting and Analysing Spaceborn Data
Collecting and Analysing Spaceborn Data
 
Collecting and Analysing Satellite Data with Azure Orbital
Collecting and Analysing Satellite Data with Azure OrbitalCollecting and Analysing Satellite Data with Azure Orbital
Collecting and Analysing Satellite Data with Azure Orbital
 
Language Studio and Custom Models
Language Studio and Custom ModelsLanguage Studio and Custom Models
Language Studio and Custom Models
 
CosmosDB for IoT Scenarios
CosmosDB for IoT ScenariosCosmosDB for IoT Scenarios
CosmosDB for IoT Scenarios
 
Forecasting time series powerful and simple
Forecasting time series powerful and simpleForecasting time series powerful and simple
Forecasting time series powerful and simple
 
Constrained Optimization with Genetic Algorithms and Project Bonsai
Constrained Optimization with Genetic Algorithms and Project BonsaiConstrained Optimization with Genetic Algorithms and Project Bonsai
Constrained Optimization with Genetic Algorithms and Project Bonsai
 
Azure security guidelines for developers
Azure security guidelines for developers Azure security guidelines for developers
Azure security guidelines for developers
 
Autonomous Machines with Project Bonsai
Autonomous Machines with Project BonsaiAutonomous Machines with Project Bonsai
Autonomous Machines with Project Bonsai
 
Global azure virtual 2021 - Azure Lighthouse
Global azure virtual 2021 - Azure LighthouseGlobal azure virtual 2021 - Azure Lighthouse
Global azure virtual 2021 - Azure Lighthouse
 
Flux QL - Nexgen Management of Time Series Inspired by JS
Flux QL - Nexgen Management of Time Series Inspired by JSFlux QL - Nexgen Management of Time Series Inspired by JS
Flux QL - Nexgen Management of Time Series Inspired by JS
 
Azure architecture design patterns - proven solutions to common challenges
Azure architecture design patterns - proven solutions to common challengesAzure architecture design patterns - proven solutions to common challenges
Azure architecture design patterns - proven solutions to common challenges
 
Industrial IoT on Azure
Industrial IoT on AzureIndustrial IoT on Azure
Industrial IoT on Azure
 
The Power of Auto ML and How Does it Work
The Power of Auto ML and How Does it WorkThe Power of Auto ML and How Does it Work
The Power of Auto ML and How Does it Work
 

Recently uploaded

Corporate Management | Session 3 of 3 | Tendenci AMS
Corporate Management | Session 3 of 3 | Tendenci AMSCorporate Management | Session 3 of 3 | Tendenci AMS
Corporate Management | Session 3 of 3 | Tendenci AMS
Tendenci - The Open Source AMS (Association Management Software)
 
Beyond Event Sourcing - Embracing CRUD for Wix Platform - Java.IL
Beyond Event Sourcing - Embracing CRUD for Wix Platform - Java.ILBeyond Event Sourcing - Embracing CRUD for Wix Platform - Java.IL
Beyond Event Sourcing - Embracing CRUD for Wix Platform - Java.IL
Natan Silnitsky
 
How to Position Your Globus Data Portal for Success Ten Good Practices
How to Position Your Globus Data Portal for Success Ten Good PracticesHow to Position Your Globus Data Portal for Success Ten Good Practices
How to Position Your Globus Data Portal for Success Ten Good Practices
Globus
 
top nidhi software solution freedownload
top nidhi software solution freedownloadtop nidhi software solution freedownload
top nidhi software solution freedownload
vrstrong314
 
Vitthal Shirke Microservices Resume Montevideo
Vitthal Shirke Microservices Resume MontevideoVitthal Shirke Microservices Resume Montevideo
Vitthal Shirke Microservices Resume Montevideo
Vitthal Shirke
 
Cracking the code review at SpringIO 2024
Cracking the code review at SpringIO 2024Cracking the code review at SpringIO 2024
Cracking the code review at SpringIO 2024
Paco van Beckhoven
 
Navigating the Metaverse: A Journey into Virtual Evolution"
Navigating the Metaverse: A Journey into Virtual Evolution"Navigating the Metaverse: A Journey into Virtual Evolution"
Navigating the Metaverse: A Journey into Virtual Evolution"
Donna Lenk
 
Webinar: Salesforce Document Management 2.0 - Smarter, Faster, Better
Webinar: Salesforce Document Management 2.0 - Smarter, Faster, BetterWebinar: Salesforce Document Management 2.0 - Smarter, Faster, Better
Webinar: Salesforce Document Management 2.0 - Smarter, Faster, Better
XfilesPro
 
Prosigns: Transforming Business with Tailored Technology Solutions
Prosigns: Transforming Business with Tailored Technology SolutionsProsigns: Transforming Business with Tailored Technology Solutions
Prosigns: Transforming Business with Tailored Technology Solutions
Prosigns
 
TROUBLESHOOTING 9 TYPES OF OUTOFMEMORYERROR
TROUBLESHOOTING 9 TYPES OF OUTOFMEMORYERRORTROUBLESHOOTING 9 TYPES OF OUTOFMEMORYERROR
TROUBLESHOOTING 9 TYPES OF OUTOFMEMORYERROR
Tier1 app
 
Globus Compute wth IRI Workflows - GlobusWorld 2024
Globus Compute wth IRI Workflows - GlobusWorld 2024Globus Compute wth IRI Workflows - GlobusWorld 2024
Globus Compute wth IRI Workflows - GlobusWorld 2024
Globus
 
Custom Healthcare Software for Managing Chronic Conditions and Remote Patient...
Custom Healthcare Software for Managing Chronic Conditions and Remote Patient...Custom Healthcare Software for Managing Chronic Conditions and Remote Patient...
Custom Healthcare Software for Managing Chronic Conditions and Remote Patient...
Mind IT Systems
 
AI Pilot Review: The World’s First Virtual Assistant Marketing Suite
AI Pilot Review: The World’s First Virtual Assistant Marketing SuiteAI Pilot Review: The World’s First Virtual Assistant Marketing Suite
AI Pilot Review: The World’s First Virtual Assistant Marketing Suite
Google
 
Understanding Globus Data Transfers with NetSage
Understanding Globus Data Transfers with NetSageUnderstanding Globus Data Transfers with NetSage
Understanding Globus Data Transfers with NetSage
Globus
 
Accelerate Enterprise Software Engineering with Platformless
Accelerate Enterprise Software Engineering with PlatformlessAccelerate Enterprise Software Engineering with Platformless
Accelerate Enterprise Software Engineering with Platformless
WSO2
 
GlobusWorld 2024 Opening Keynote session
GlobusWorld 2024 Opening Keynote sessionGlobusWorld 2024 Opening Keynote session
GlobusWorld 2024 Opening Keynote session
Globus
 
Large Language Models and the End of Programming
Large Language Models and the End of ProgrammingLarge Language Models and the End of Programming
Large Language Models and the End of Programming
Matt Welsh
 
Top Features to Include in Your Winzo Clone App for Business Growth (4).pptx
Top Features to Include in Your Winzo Clone App for Business Growth (4).pptxTop Features to Include in Your Winzo Clone App for Business Growth (4).pptx
Top Features to Include in Your Winzo Clone App for Business Growth (4).pptx
rickgrimesss22
 
A Comprehensive Look at Generative AI in Retail App Testing.pdf
A Comprehensive Look at Generative AI in Retail App Testing.pdfA Comprehensive Look at Generative AI in Retail App Testing.pdf
A Comprehensive Look at Generative AI in Retail App Testing.pdf
kalichargn70th171
 
Enhancing Research Orchestration Capabilities at ORNL.pdf
Enhancing Research Orchestration Capabilities at ORNL.pdfEnhancing Research Orchestration Capabilities at ORNL.pdf
Enhancing Research Orchestration Capabilities at ORNL.pdf
Globus
 

Recently uploaded (20)

Corporate Management | Session 3 of 3 | Tendenci AMS
Corporate Management | Session 3 of 3 | Tendenci AMSCorporate Management | Session 3 of 3 | Tendenci AMS
Corporate Management | Session 3 of 3 | Tendenci AMS
 
Beyond Event Sourcing - Embracing CRUD for Wix Platform - Java.IL
Beyond Event Sourcing - Embracing CRUD for Wix Platform - Java.ILBeyond Event Sourcing - Embracing CRUD for Wix Platform - Java.IL
Beyond Event Sourcing - Embracing CRUD for Wix Platform - Java.IL
 
How to Position Your Globus Data Portal for Success Ten Good Practices
How to Position Your Globus Data Portal for Success Ten Good PracticesHow to Position Your Globus Data Portal for Success Ten Good Practices
How to Position Your Globus Data Portal for Success Ten Good Practices
 
top nidhi software solution freedownload
top nidhi software solution freedownloadtop nidhi software solution freedownload
top nidhi software solution freedownload
 
Vitthal Shirke Microservices Resume Montevideo
Vitthal Shirke Microservices Resume MontevideoVitthal Shirke Microservices Resume Montevideo
Vitthal Shirke Microservices Resume Montevideo
 
Cracking the code review at SpringIO 2024
Cracking the code review at SpringIO 2024Cracking the code review at SpringIO 2024
Cracking the code review at SpringIO 2024
 
Navigating the Metaverse: A Journey into Virtual Evolution"
Navigating the Metaverse: A Journey into Virtual Evolution"Navigating the Metaverse: A Journey into Virtual Evolution"
Navigating the Metaverse: A Journey into Virtual Evolution"
 
Webinar: Salesforce Document Management 2.0 - Smarter, Faster, Better
Webinar: Salesforce Document Management 2.0 - Smarter, Faster, BetterWebinar: Salesforce Document Management 2.0 - Smarter, Faster, Better
Webinar: Salesforce Document Management 2.0 - Smarter, Faster, Better
 
Prosigns: Transforming Business with Tailored Technology Solutions
Prosigns: Transforming Business with Tailored Technology SolutionsProsigns: Transforming Business with Tailored Technology Solutions
Prosigns: Transforming Business with Tailored Technology Solutions
 
TROUBLESHOOTING 9 TYPES OF OUTOFMEMORYERROR
TROUBLESHOOTING 9 TYPES OF OUTOFMEMORYERRORTROUBLESHOOTING 9 TYPES OF OUTOFMEMORYERROR
TROUBLESHOOTING 9 TYPES OF OUTOFMEMORYERROR
 
Globus Compute wth IRI Workflows - GlobusWorld 2024
Globus Compute wth IRI Workflows - GlobusWorld 2024Globus Compute wth IRI Workflows - GlobusWorld 2024
Globus Compute wth IRI Workflows - GlobusWorld 2024
 
Custom Healthcare Software for Managing Chronic Conditions and Remote Patient...
Custom Healthcare Software for Managing Chronic Conditions and Remote Patient...Custom Healthcare Software for Managing Chronic Conditions and Remote Patient...
Custom Healthcare Software for Managing Chronic Conditions and Remote Patient...
 
AI Pilot Review: The World’s First Virtual Assistant Marketing Suite
AI Pilot Review: The World’s First Virtual Assistant Marketing SuiteAI Pilot Review: The World’s First Virtual Assistant Marketing Suite
AI Pilot Review: The World’s First Virtual Assistant Marketing Suite
 
Understanding Globus Data Transfers with NetSage
Understanding Globus Data Transfers with NetSageUnderstanding Globus Data Transfers with NetSage
Understanding Globus Data Transfers with NetSage
 
Accelerate Enterprise Software Engineering with Platformless
Accelerate Enterprise Software Engineering with PlatformlessAccelerate Enterprise Software Engineering with Platformless
Accelerate Enterprise Software Engineering with Platformless
 
GlobusWorld 2024 Opening Keynote session
GlobusWorld 2024 Opening Keynote sessionGlobusWorld 2024 Opening Keynote session
GlobusWorld 2024 Opening Keynote session
 
Large Language Models and the End of Programming
Large Language Models and the End of ProgrammingLarge Language Models and the End of Programming
Large Language Models and the End of Programming
 
Top Features to Include in Your Winzo Clone App for Business Growth (4).pptx
Top Features to Include in Your Winzo Clone App for Business Growth (4).pptxTop Features to Include in Your Winzo Clone App for Business Growth (4).pptx
Top Features to Include in Your Winzo Clone App for Business Growth (4).pptx
 
A Comprehensive Look at Generative AI in Retail App Testing.pdf
A Comprehensive Look at Generative AI in Retail App Testing.pdfA Comprehensive Look at Generative AI in Retail App Testing.pdf
A Comprehensive Look at Generative AI in Retail App Testing.pdf
 
Enhancing Research Orchestration Capabilities at ORNL.pdf
Enhancing Research Orchestration Capabilities at ORNL.pdfEnhancing Research Orchestration Capabilities at ORNL.pdf
Enhancing Research Orchestration Capabilities at ORNL.pdf
 

Machine Learning at Hand with Power BI

  • 1. April 27 GLOBAL AZURE BOOTCAMP IS POWERED BY: Machine Learning at Hand with Power BI How Developers and Data Scientists could Bring AI to the Business User
  • 2. Thanks to our Sponsors: Global Sponsor: Platinum Sponsors: Gold Sponsors: Silver Sponsors: Swag Sponsor: General Sponsor:
  • 3. About me • Software Architect @ o 17+ years professional experience • Microsoft Azure MVP • External Expert Horizon 2020 • External Expert Eurostars-Eureka, InnoFund Denmark • Business Interests o Web Development, SOA, Integration o IoT, Machine Learning, Computer Intelligence o Security & Performance Optimization • Contact ivelin.andreev@icb.bg www.linkedin.com/in/ivelin www.slideshare.net/ivoandreev
  • 4. AGENDA The ML Hype The ML Features in PBI PBI Premium, Pro, Embedded Auto ML Quick Insights Text Analytics Key Influencers Custom R/Python Demo
  • 5. “Difference between ML and AI? - If it is written in Python, probably it is ML. - If it is written in PowerPoint, probably it is AI.” * * * “When you’re fundraising, it’s AI. When you’re hiring, it’s ML. When you’re implementing, it’s linear regression.“ * * * “How many data scientists it takes to change a light bulb? (A data scientist at heart would say “None, as it is a HW problem”) In fact it is 20 seniors and 1 intern. Data scientists will argue over a month on the right approach, the intern will copy the solution from StackOverflow.” Wondering why AI does not Provide the Expected
  • 6. Gartner’s Hype Cycle 3. Trough of disillusionment 4. Slope of enlightment 5. Plateau of productivity Expectations Time 1. Technology Launch generates significant interest 2. A peak of inflated expectations
  • 7. “Business impact from AI initiatives takes much longer than anticipated” * * * “Classical ML techniques are extremely underrated.” * * * “…many organizations are pushing to apply deep learning techniques without even understanding how they apply to their current initiatives.” * * * “Through 2022, over 75% of organizations will use DNNs for use cases that could be addressed using classical ML techniques” Chirag Dekate, Sr. Research Director
  • 8. Hype Cycle for Midsize Enterprises, 2018
  • 9. Users are Drowning in Data • Environment generates massive data volumes • Understanding requires AI for exploration • Users are asking to get insights with no code The Microsoft Approach • Place AI in the hands of the end-users • Expose backend data science work
  • 10. Microsoft Place AI in the Hands of End-Users • Azure Cognitive Services o ML algorithms to extract information from unstructured sources o Vision, speech and facial recognition, language understanding • Key Driver Analysis o Help users understand what combination of impact features determines a KPI o Automatically point most important factors • Integrate ML models in PBI o Azure ML models shared by data scientists to business analysts • Own ML Models in PBI o Business Analysts produce own ML models without writing code o Use Automated ML features targeting users, rather than developers
  • 11. PBI Target Audience, Licensing and Pricing • PBI Portfolio o On-Premises: Desktop, Mobile, Report Server o Service: Free, Pro, Premium(EM/P SKU), Embedded (A SKU) • New AI features N/A in Pro o AI Preview requires A2 SKU but provisioning fails on A2 SKU o Hint: Create on A4, downscale to A2 • “A” SKUs identical to “EM/P” o Pro – 8.8 EUR User/ М (Shared) o A1 SKU – 630 EUR / M (equals EM1) o A2 SKU – 1’256 EUR / M (equals EM2) o A3 SKU – 2’518 EUR / M (equals EM3) o A4 SKU – 5’041 EUR / M (equals P1) o A5 SKU – 10’087 EUR / M (equals P2) o A6 SKU – 20’180 EUR / M (equals P3) PBI User Licensing PBI Free PBI Pro Capacity Licensing P SKU EM SKU A SKU A SKU EM SKU P SKU Purchase Azure O365 O365 Sharing Use Case Embedded rep. Embedded rep. SharePoint MS Teams Embedded rep. SharePoint MS Teams PBI Apps Billing Hourly Monthly Monthly Commitment No Year/Month Year/Month
  • 12. PBI Service - Pro vs Premium PRO PREMIUM Highlights License individual users • Create content • Consume content License capacity to serve multiple users: • No additional cost to view content • Creators still need PBI Pro Size Small-medium deployments (i.e. 200 users) Cost efficient from 500 viewers Cost Calculator: https://powerbi.microsoft.com/en-us/calculator/ Hardware • Shared capacity=shared resources • Limitations ensure QoS (1GB file size) • Dedicated hardware, consistent performance • Larger data volumes (10GB file size) Functionality • Dataset refresh - 8 times / 24h • Dataset refresh – 48 times / 24h • PBI Report Server • Data flows • AI workloads • Embedded deployment • Sharing, Personalization, Geolocation
  • 13. Power BI Pro AI Features • Key Influencers • Quick Insights • Cognitive services (manual) • Python / R script Power BI Premium AI Features • AI insights & Cognitive Services • Automated ML
  • 14. Automated ML in PBI (Preview) • Enables Business Analyst to create and train model directly in PBI • Requires Premium Workspace • Supports Binary Prediction, Classification and Regression models • Auto ML Service automatically o Extracts meaningful parameters from query o Splits data in training and validation dataset o Performs training with multiple models o Summarizes accuracy of model o Apply model to future data for predictive insights o AI insights allow direct access to Cognitive services https://sqlbits.com/Sessions/Event18/Power_BI_Premium_on_a_budget https://docs.microsoft.com/en-us/power-bi/service-machine-learning-automated
  • 18. PBI Desktop Quick Insights Use insights in Power BI Desktop to explain increases and decreases seen in visuals Text Analytics Use Azure Cognitive Services text analytics APIs to enrich dataset in PBI M Query
  • 19. Quick Insights What is “Quick Insights”: • Sophisticated ML against dataset and output to formatted visuals • Output visuals can be integrated in reports How it works: o PBI Service: Datasets > … > “Generate Quick Insights” o PBI Desktop: Data point > right-click > “Analyze” Key Limitations: o Not executed against DirectQuery, Streaming and Live connect o Non-numeric measures are not supported o Power BI Desktop is limited to the local dataset
  • 20. Text Analytics in Azure with Power BI • What is “Text Analytics”: o Identify meaning and topics from unstructured data • Limitations: o Up to 17 languages supported (Apr 2019) • How it works: o Register Azure Cognitive Services Text API Key o M-language query from new Power Query
  • 21. Text Analytics (Step by Step) 1. Create new query in left queries panel 2. Open View > “Advanced Editor” 3. Write the M-code function query 4. On target query, add function column 5. Set column, func. query and parameter 6. Use column in report (i.e. WordCloud) ➀➁ ➂ ➃ ➄ 
  • 22. Key Influencers Visual Explain the factors that drive a metric of interest Top Segments Explain what combination of factors are most influential
  • 23. Key Influencers (preview) One of the key ML usages is to find hidden insights What is “Key Influencers”: • Understand factors that impact a metric of interest • Understand the importance of each factor • Top segment factor combinations Limitations o Works for categorical & numeric fields o Not supported for measures and aggregates o Not supported in PBI Embedded and Mobile Note: Increasing the number of categories to analyze means there are fewer observations per category.
  • 24. The Key Influencers Visual 1. Tabs o Top contributors / Top segments 2. Metric of interest 3. Restatements o Help to interpret the pane visuals 4. Average line o Determined by factors in black 5. Checkbox o Show only influencers ➀ ➁ ➂ ➂ ➃ ➄
  • 25. The Top Segments Visual 1. Impact of combination of factors on metric 2. Metric of interest 3. Order of segments o Ranked by % of metric of interest o Higher proportion ⇨ higher bubble 4. Segment distribution details o Number of data points ⇨ size of segments 5. Drill down o Segment details and deep dive ➁ ➃ ➀ ➂ ➄ ➄
  • 26. How does Key Influencers Work Key Influencers • Runs on ML.NET framework • Logistic regression to search patterns • For target category o Split data points “Category” vs “Not the Category” o Determine features that distinguish two classes • Features with little data points are not considered factors Top Segments • Runs on ML.NET framework • Decision trees to find subgroups • For each factor o Decide on best split o Check representative set reached • Filters are grouped into segments
  • 27. Custom AI with Python/R PBI models with custom and R/Python visuals
  • 28. Custom AI with Python/R • PBI Visuals & Power Query with Python since Feb 2019 (preview Aug 2018) • PBI Desktop automatically detects runtimes o Install: https://www.python.org/downloads/, https://www.rstudio.com/ o Packages: pip install [name]; install.packages(‘[name]', dependencies = TRUE) • Very good for interactive reports trained from past data • Key Limitations o 150’000 rows, 250MB, 2MB image, 1 GB RAM o 60s (Service) / 300s (Desktop) o PBI Service: limited packages; Python 2.7 and 3.7 • Python IDEs (write and debug Python script) o Jupyter NB? ML Workbench? VS2019 Python Support
  • 29. PBI Prediction with Custom Model https://towardsdatascience.com/how-to-predict-values-from-a-custom-r-model-in-power-bi-3364f83b0015 * Publish to web is currently not supported for R visuals (April 2019)
  • 30. Takeaways & References • About Automated Machine Learning o https://docs.microsoft.com/en-us/azure/machine-learning/service/concept-automated-ml • Power BI Guided Learning o https://docs.microsoft.com/en-us/power-bi/guided-learning/ • Azure Data-AI-IoT (Samples, Training & Tutorials) o https://github.com/Azure/data-ai-iot • PBI for Data Science o https://www.pbiusergroup.com/communities/community- home?CommunityKey=5b43099c-d801-49ed-af87-f1da8311f41e • PBI Samples o https://docs.microsoft.com/en-us/power-bi/sample-datasets • Starter Books
  • 31. Microsoft Power BI ServiceMicrosoft Power BI Desktop
  • 32. Thanks to our Sponsors: Global Sponsor: Platinum Sponsors: Gold Sponsors: Silver Sponsors: Swag Sponsor: General Sponsor: