The document discusses a SharePoint conference presentation by Bhakthi Liyanage on machine learning, emphasizing its definition and various applications within data analysis. It covers the machine learning lifecycle, from defining objectives and collecting data to training and evaluating models, showcasing the importance of proper data preparation and integration. Additionally, it highlights Azure Machine Learning as a powerful tool that enables rapid deployment of predictive analytics solutions.

1. Bhakthi Liyanage
SharePoint Saturday Charlotte
17 September 2016

2. @CASPUG #SPSCLT16
Platinum
Gold
SilverandBronze
Charlotte SharePoint Community!



THANK YOU
EVENT SPONSORS!

3. @CASPUG #SPSCLT16
PLEASE TELL US WHAT YOU THINK
http://bit.do/SPSCLT16

4. @CASPUG #SPSCLT16
CONFERENCE COMMUNICATION

lanyrd.com/2016/spsclt16

@CASPUG #SPSCLT16

info@casug.org

5. • Who am I?
• Introducing machine learning
• Introducing Azure Machine Learning
• Machine Learning Lifecycle
• Demo
• Summary
• Q & A

6. 6
Sr. SharePoint Architect
16+ years in the IT industry
11+ years in SharePoint
bhakthil@gmail.com
@bhakthil
https://www.linkedin.com/pub/bhakthi-
liyanage/14/15/912
https://github.com/bhakthil

8. Academic Definition
Machine learning is a subfield of computer science that evolved
from the study of pattern recognition and computational learning
theory in artificial intelligence. Machine learning explores the
study and construction of algorithms that can learn from and
make predictions on data.
Simple Definition
Computing systems that become smarter with learning and
experience
Experience = Past data + human input

9. • Need to know of the future

10. • Being able to predict the future with a reasonable accuracy
Reports
Yesterday Today Tomorrow
Business Intelligence
Predictive Analytics
Predictability
Time

11. A highly educated and skilled person who can solve complex data problems by
employing deep expertise in scientific disciplines (mathematics, statistics or
computer science)
A skilled person who creates or maintains data systems, data solutions, or
implements predictive modelling
Roles: Database Administrator, Database Developer, or BI Developer
A skilled person who designs and develops programming logic, and can apply
machine learning to integrate predictive functionality into applications

12.  What problems are we
trying to solve?
◦ Anomaly detection
◦ Customer churn
◦ Predictive maintenance
◦ Recommendations system
 What data do we have or
do we have any data at
all?
◦ Data already available via sensory
systems, transactional databases,
customer sales databases, etc.
Predictive
maintenance
Vision
Analytics
Recommenda-
tion engines
Advertising
analysis
Weather
forecasting for
business
planning
Social network
analysis
Legal
discovery and
document
archiving
Pricing analysis
Fraud
detection
Churn
analysis
Equipment
monitoring
Location-
based tracking
and services
Personalized
Insurance

13.  Data Consist of
◦ Features (aka input parameters) : The data that
is fed in to the model
◦ Identify which features relevant for the problem
◦ Labels : Historical result of each observation
 Training Data
◦ Pairing of features and label
◦ Historical
 Data Validation
◦ Used to verify the trained model

14.  Supervised
◦ Machine learning task of inferring a function/model from labeled
training data or examples
◦ Training data consist of both features and labels
 Un-supervised
◦ Machine learning task of inferring a function to describe hidden
structure from unlabeled data
◦ Data contains only features

16.  Enables powerful cloud-based predictive analytics
 Professionals can easily build, deploy and share
advanced analytics solutions
 Browser based, Rapid Deployment
 Connects seamlessly with other Azure data-related services,
including:
 Azure HDInsight (Big Data)
 Azure SQL Database, and
 Virtual Machines
 Models are consumed via ML API service

17. Machine learning lifecycle
Define
Objective
Collect
Data
Prepare
Data
Train
Models
Evaluate
Models
Deploy
Manage
Integrate

18.  It is important to start a machine learning project with a
clearly defined objective
I need to predict
customer churn rate
for next 6 months…
Define
Objective
I need to suggest
relevant products to
the customers
I need to know when
my manufacturing
equipment will fail

19.  Collecting complete data is critical
◦ Garbage in ► Garbage out 
 Datasets can be sourced from:
◦ Internal sources, i.e. operational systems, data warehouse, etc.
◦ External sources
◦ Different formats, i.e. relational, multidimensional, text, map-
reduce
 Combining datasets can enrich data
◦ E.g., integrate internal data to external data like weather, or
market intelligence data
◦ Weather data with flight delay data
◦ Population data with energy consumption data
Collect
Data

20.  Prepare data for machine learning
◦ Transform to cleanse, reduce or reformat
◦ Isolate and flag abnormal data
◦ Appropriately substitute missing values
◦ Categorize continuous values into ranges
◦ Normalize continuous values between 0 and 1
 Of course, having the required data to begin with is
important
◦ When designing systems, give consideration to attributes that
may be required as inputs for future modeling, e.g.
demographic data: Birth date, gender, etc.
Prepare
Data

21.  This stage is iterative, and experimentation involves:
◦ Selecting a machine learning algorithm
◦ Defining inputs and outputs
◦ Optimizing by configuring algorithm parameters
 Model evaluation is critical to determine:
◦ Accuracy, Reliability, Usefulness
Train
Models
Evaluate
Models

22.  First, add a scoring experiment
– Training logic is replaced with a trained model
– Inputs and output end-points are added
– Module properties can be parameterized
 Publish the experiment to the gallery
– Learn from others by discovering experiments
– Contribute and showcase your experiments
Deploy

23. Integrate
 Integrate the experiment with external applications
– Integration offers REST web service end points
– Each web service offers two methods:
• Request/Response Service (RRS) ► Low latency, highly scalable web
service
• Batch Execution Service (BES) ► High volume, asynchronous scoring of
many records

24. Stream analytics, blob
storage,
Azure SQL, HDInsight
Azure ML Services
Clients
Azure ML
Studio
ML web service end-
points
Data Model Development Model Deployment Operationalize

25. Power BI/DashboardsMobile AppsWeb Apps
Azure Portal
Azure Ops Team
ML Studio
Data Scientist
HDInsight
Azure Storage
Desktop Data
Azure Portal &
ML API service
Azure Ops Team
ML API service Developer
ML Studio
and the Data Professional
• Access and prepare data
• Create, test and train models
• Collaborate
• One click to stage for
production via the API service
AzurePortal&MLAPIservice
and the Azure Ops Team
• Create ML Studio workspace
• Assign storage account(s)
• Monitor ML consumption
• See alerts when model is ready
• Deploy models to web service
ML API service and the Application Developer
• Tested models available as a URL that can be called from any endpoint
Business users easily access results
from anywhere, on any device

27. Machine Learning is a subfield of computer science and
statistics that deals with the construction and study of
systems that can learn from data.
Azure Machine Learning key attributes:
Fully managed ► No hardware or software to buy
Integrated ► Drag, drop, connect and configure
Best-in-class algorithms ► Proven solutions from Xbox and Bing
R built in ► Use over 400 R packages, or bring your own R or Python code
Deploy in minutes ► Operationalize with a click
Flexible consumption ► Any device capable of consuming REST API
Machine Learning is now approachable to developers

28. JOIN US FOR SHAREPINT
 Immediately following today’s
event
 First drink is on us
 Brink your event ticket for
validation
 Duckworth’s Grill & Taphouse
330 North Tryon Street
Charlotte, NC 28202
(7th and Tryon)

29. Q & A