SlideShare une entreprise Scribd logo
1  sur  88
Télécharger pour lire hors ligne
Intro to Machine Learning

for web folks
“Machine Learning, je m’y mets dès demain”
@louisdorard
#blendwebmix 2015
–Mike Gualtieri, Principal Analyst at Forrester
“Predictive apps are
the next big thing
in app development.”
Lars Trieloff
@trieloff
(see source)
–Waqar Hasan, VISA
“Predictive is the ‘killer app’ for big
data.”
Amazon for David Jones (@d_jones, see source)
Amazon for David Jones (@d_jones, see source)
1. Machine Learning
2. Data
TECH ??
–Charles Parker, PhD, Allston Trading
“ML isn’t about ML”
BIZ
DESIGN
RECH
code
code
code
BLEND !!
@louisdorard
Intro to machine learning for web folks @ BlendWebMix
“Where makers of Predictive APIs and apps meet”
Machine Learning
Use cases
Limitations
Modern tools
Case study
ML Canvas
Demystifying

Machine Learning
Intro to machine learning for web folks @ BlendWebMix
“Which type of email is this?
— Spam/Ham”


“Which type of email is this?
— Spam/Ham”


Classification
I
O
“Which type of email is this?
— Spam/Ham”


??
Intro to machine learning for web folks @ BlendWebMix
“How much is this house worth?
— X $”


-> Regression
Bedrooms Bathrooms Surface (foot²) Year built Type Price ($)
3 1 860 1950 house 565,000
3 1 1012 1951 house
2 1.5 968 1976 townhouse 447,000
4 1315 1950 house 648,000
3 2 1599 1964 house
3 2 987 1951 townhouse 790,000
1 1 530 2007 condo 122,000
4 2 1574 1964 house 835,000
4 2001 house 855,000
3 2.5 1472 2005 house
4 3.5 1714 2005 townhouse
2 2 1113 1999 condo
1 769 1999 condo 315,000
Bedrooms Bathrooms Surface (foot²) Year built Type Price ($)
3 1 860 1950 house 565,000
3 1 1012 1951 house
2 1.5 968 1976 townhouse 447,000
4 1315 1950 house 648,000
3 2 1599 1964 house
3 2 987 1951 townhouse 790,000
1 1 530 2007 condo 122,000
4 2 1574 1964 house 835,000
4 2001 house 855,000
3 2.5 1472 2005 house
4 3.5 1714 2005 townhouse
2 2 1113 1999 condo
1 769 1999 condo 315,000
Intro to machine learning for web folks @ BlendWebMix
ML is a set of AI techniques where
“intelligence” is built by referring to
examples
Intro to machine learning for web folks @ BlendWebMix
Use cases
• Real-estate
• Spam
• Priority inbox
• Crowd prediction
property price
email spam indicator
email importance indicator
location & context #people
Zillow
Gmail
Gmail
Tranquilien
I. Get more customers
• Reduce churn
• Score leads
• Optimize campaigns
customer churn indicator
customer revenue
customer & campaign interest indicator
II. Serve customers better
• Cross-sell
• Increase engagement
• Optimize pricing
customer & product purchase indicator
user & item interest indicator
product & price #sales
III. Serve customers more efficiently
• Predict demand
• Automate tasks
• Use predictive enterprise apps
context demand
credit application repayment indicator
Predictive enterprise apps
• Priority filtering
• Message routing
• Auto-configuration
message priority indicator
request employee
user & actions settings
RULES
–Katherine Barr, Partner at VC-firm MDV
"Pairing human workers with
machine learning and automation
will transform knowledge work
and unleash new levels of human
productivity and creativity."
Limitations
Intro to machine learning for web folks @ BlendWebMix
Intro to machine learning for web folks @ BlendWebMix
Intro to machine learning for web folks @ BlendWebMix
Intro to machine learning for web folks @ BlendWebMix
Need examples of inputs AND outputs
Intro to machine learning for web folks @ BlendWebMix
What if not enough data points?
Intro to machine learning for web folks @ BlendWebMix
What if similar inputs have dissimilar outputs?
Intro to machine learning for web folks @ BlendWebMix
Bedrooms Bathrooms Price ($)
3 2 500,000
3 2 800,000
1 1 300,000
1 1 800,000
Bedrooms Bathrooms Surface (foot²) Year built Price ($)
3 2 800 1950 500,000
3 2 1000 1950 800,000
1 1 500 1950 300,000
1 1 500 2014 800,000
• Need examples of inputs AND outputs
• Need enough examples
• Need enough“features”
–@louisdorard
“A model can only be as good as
the data it was given to train on”
–McKinsey & Co. (2011)
“A significant constraint on
realizing value from big data will
be a shortage of talent,
particularly of people with deep
expertise in statistics and machine
learning.”
MLaaS & Predictive APIs:

ML for all
Intro to machine learning for web folks @ BlendWebMix
HTML / CSS / JavaScript
HTML / CSS / JavaScript
squarespace.com
Intro to machine learning for web folks @ BlendWebMix
Intro to machine learning for web folks @ BlendWebMix
The two phases of machine learning:
• TRAIN a model
• PREDICT with a model
The two methods of predictive APIs:
• TRAIN a model
• PREDICT with a model
The two methods of predictive APIs:
• model = create_model(dataset)
• predicted_output =
create_prediction(model, new_input)
The two methods of predictive APIs:
• model = create_model(‘training.csv’)
• predicted_output =
create_prediction(model, new_input)
Intro to machine learning for web folks @ BlendWebMix
Intro to machine learning for web folks @ BlendWebMix
Intro to machine learning for web folks @ BlendWebMix
From Large to Small & Medium Enterprises
• recommendations in e-commerce
• => 71% increase in revenue
• churn detection
• => 11% increase in retention
ChurnSpotter.io
Microsoft Azure ML
PredictionIO
Intro to machine learning for web folks @ BlendWebMix
Case study:

churn analysis
• Who: SaaS company selling monthly subscription
• Question asked:“Is this customer going to leave
within 1 month?”
• Input: customer
• Output: no-churn or churn
• Data collection: history up until 1 month ago
• Baseline: if no usage for more than 15 days then
churn
Learning: OK
but
• How to represent customers?
• What to do after predicting churn?
Customer representation:
• basic info (age, income, etc.)
• usage of service (# times used app, avg time spent,
features used, etc.)
• interactions with customer support (how many,
topics of questions, satisfaction ratings)
Taking action to prevent churn:
• contact customers (in which order?)
• switch to different plan
• give special offer
• no action?
Measuring accuracy:
• #TP (we predict customer churns and he does)
• #FP (we predict customer churns but he doesn’t)
• #FN (we predict customer doesn’t churn but he does)
• Compare to heuristic/baseline
Return On Investment:
• Taking action for each TP (and FP) has a cost
• For each TP we“gain”:

(success rate of action) * (revenue /cust. /month)
• Imagine…
• perfect predictions
• revenue /cust. /month = 10€
• success rate of action = 20%
• cost of action = 2€
• Which ROI?
Machine Learning
Canvas
Intro to machine learning for web folks @ BlendWebMix
PREDICTIONS OBJECTIVES DATA
Context
Who will use the predictive system / who will be
affected by it? Provide some background.
Value Proposition
What are we trying to do? E.g. spend less time on
X, increase Y...
Data Sources
Where do/can we get data from? (internal
database, 3rd party API, etc.)
Problem
Question to predict answers to (in plain English)
Input (i.e. question "parameter")
Possible outputs (i.e. "answers")
Type of problem (e.g. classification, regression,
recommendation...)
Baseline
What is an alternative way of making predictions
(e.g. manual rules based on feature values)?
Performance evaluation
Domain-specific / bottom-line metrics for
monitoring performance in production
Prediction accuracy metrics (e.g. MSE if
regression; % accuracy, #FP for classification)
Offline performance evaluation method (e.g.
cross-validation or simple training/test split)
Dataset
How do we collect data (inputs and outputs)?
How many data points?
Features
Used to represent inputs and extracted from
data sources above. Group by types and
mention key features if too many to list all.
Using predictions
When do we make predictions and how many?
What is the time constraint for making those predictions?
How do we use predictions and confidence values?
Learning predictive models
When do we create/update models? With which data / how much?
What is the time constraint for creating a model?
Criteria for deploying model (e.g. minimum performance value — absolute,
relative to baseline or to previous model)
IDEASPECSDEPLOYMENT
BACKGROUND
ENGINE SPECS
INTEGRATION
PREDICTIONS OBJECTIVES DATA
BACKGROUND
ENGINE SPECS
INTEGRATION
PREDICTIONS OBJECTIVES DATA
BACKGROUND End-user Value prop Sources
ENGINE SPECS ML problem Perf eval Preparation
INTEGRATION Using pred Learning modelINTEGRATION Using pred Learning model
Why fill in ML canvas?
• Target the right problem for your company
• Choose right algorithm, infrastructure, or ML
solution
• Guide project management
• Improve team communication
machinelearningcanvas.com
Recap
• ML to create value from data
• 2 phases: TRAIN and PREDICT
• MLaaS & Predictive APIs make it more accessible
• Good data is essential
• What do we do with predictions?
• Accuracy is not the objective! A/B test?
• Start with the ML Canvas
• Later: deploy, maintain, improve…
@louisdorard
louisdorard.com

Contenu connexe

Tendances

Building a Production-ready Predictive App for Customer Service - Alex Ingerm...
Building a Production-ready Predictive App for Customer Service - Alex Ingerm...Building a Production-ready Predictive App for Customer Service - Alex Ingerm...
Building a Production-ready Predictive App for Customer Service - Alex Ingerm...PAPIs.io
 
Pragmatic machine learning for the real world
Pragmatic machine learning for the real worldPragmatic machine learning for the real world
Pragmatic machine learning for the real worldLouis Dorard
 
A developer's overview of the world of predictive APIs
A developer's overview of the world of predictive APIsA developer's overview of the world of predictive APIs
A developer's overview of the world of predictive APIsLouis Dorard
 
VSSML18 Introduction to Supervised Learning
VSSML18 Introduction to Supervised LearningVSSML18 Introduction to Supervised Learning
VSSML18 Introduction to Supervised LearningBigML, Inc
 
Predictive APIs at APIdays Berlin
Predictive APIs at APIdays BerlinPredictive APIs at APIdays Berlin
Predictive APIs at APIdays BerlinLouis Dorard
 
DutchMLSchool. ML Automation
DutchMLSchool. ML AutomationDutchMLSchool. ML Automation
DutchMLSchool. ML AutomationBigML, Inc
 
Webinar - Product Matching - Palombo (20160428)
Webinar - Product Matching - Palombo (20160428)Webinar - Product Matching - Palombo (20160428)
Webinar - Product Matching - Palombo (20160428)Turi, Inc.
 
MLSEV Virtual. ML: Business Perspective
MLSEV Virtual. ML: Business PerspectiveMLSEV Virtual. ML: Business Perspective
MLSEV Virtual. ML: Business PerspectiveBigML, Inc
 

Tendances (9)

Building a Production-ready Predictive App for Customer Service - Alex Ingerm...
Building a Production-ready Predictive App for Customer Service - Alex Ingerm...Building a Production-ready Predictive App for Customer Service - Alex Ingerm...
Building a Production-ready Predictive App for Customer Service - Alex Ingerm...
 
Pragmatic machine learning for the real world
Pragmatic machine learning for the real worldPragmatic machine learning for the real world
Pragmatic machine learning for the real world
 
A developer's overview of the world of predictive APIs
A developer's overview of the world of predictive APIsA developer's overview of the world of predictive APIs
A developer's overview of the world of predictive APIs
 
VSSML18 Introduction to Supervised Learning
VSSML18 Introduction to Supervised LearningVSSML18 Introduction to Supervised Learning
VSSML18 Introduction to Supervised Learning
 
Predictive APIs at APIdays Berlin
Predictive APIs at APIdays BerlinPredictive APIs at APIdays Berlin
Predictive APIs at APIdays Berlin
 
H2o storm
H2o stormH2o storm
H2o storm
 
DutchMLSchool. ML Automation
DutchMLSchool. ML AutomationDutchMLSchool. ML Automation
DutchMLSchool. ML Automation
 
Webinar - Product Matching - Palombo (20160428)
Webinar - Product Matching - Palombo (20160428)Webinar - Product Matching - Palombo (20160428)
Webinar - Product Matching - Palombo (20160428)
 
MLSEV Virtual. ML: Business Perspective
MLSEV Virtual. ML: Business PerspectiveMLSEV Virtual. ML: Business Perspective
MLSEV Virtual. ML: Business Perspective
 

En vedette

The State of Streaming Analytics: The Need for Speed and Scale
The State of Streaming Analytics: The Need for Speed and ScaleThe State of Streaming Analytics: The Need for Speed and Scale
The State of Streaming Analytics: The Need for Speed and ScaleVoltDB
 
Why And How To Leverage Predictive APIs In Any Application
Why And How To Leverage Predictive APIs In Any Application Why And How To Leverage Predictive APIs In Any Application
Why And How To Leverage Predictive APIs In Any Application ProgrammableWeb
 
Semantic Computing Executive Briefing
Semantic Computing Executive Briefing Semantic Computing Executive Briefing
Semantic Computing Executive Briefing Graeme Wood
 
Machine Learning Intro Session
Machine Learning Intro SessionMachine Learning Intro Session
Machine Learning Intro SessionNaveen Rajan
 
Intro to modelling-supervised learning
Intro to modelling-supervised learningIntro to modelling-supervised learning
Intro to modelling-supervised learningJustin Sebok
 
Lecture 02 introduction to ai
Lecture 02 introduction to aiLecture 02 introduction to ai
Lecture 02 introduction to aiHema Kashyap
 
Machine learning intro
Machine learning introMachine learning intro
Machine learning introSergey Shelpuk
 
Intro to Machine Learning
Intro to Machine LearningIntro to Machine Learning
Intro to Machine LearningMohammed Ashour
 
Basics of Machine Learning
Basics of Machine LearningBasics of Machine Learning
Basics of Machine LearningFrank Evans
 
Machine learning
Machine learningMachine learning
Machine learningpdingles
 
Evaluating Big Data Predictive Analytics Platforms
Evaluating Big Data Predictive Analytics PlatformsEvaluating Big Data Predictive Analytics Platforms
Evaluating Big Data Predictive Analytics PlatformsTeradata Aster
 
Commercializing legal AI research: lessons learned
Commercializing legal AI research: lessons learnedCommercializing legal AI research: lessons learned
Commercializing legal AI research: lessons learnedAnna Ronkainen
 
An Intuitive Intro To Machine Learning
An Intuitive Intro To Machine LearningAn Intuitive Intro To Machine Learning
An Intuitive Intro To Machine LearningBen Freundorfer
 
AI in legal practice – the research perspective
AI in legal practice – the research perspectiveAI in legal practice – the research perspective
AI in legal practice – the research perspectiveAnna Ronkainen
 
Basics of Machine Learning
Basics of Machine LearningBasics of Machine Learning
Basics of Machine LearningPranav Challa
 
Artificial intelligence
Artificial intelligenceArtificial intelligence
Artificial intelligenceUmesh Meher
 
An introduction to AI (artificial intelligence)
An introduction to AI (artificial intelligence)An introduction to AI (artificial intelligence)
An introduction to AI (artificial intelligence)Bellaj Badr
 
Machine learning basics using trees algorithm (Random forest, Gradient Boosting)
Machine learning basics using trees algorithm (Random forest, Gradient Boosting)Machine learning basics using trees algorithm (Random forest, Gradient Boosting)
Machine learning basics using trees algorithm (Random forest, Gradient Boosting)Parth Khare
 
What AI is and examples of how it is used in legal
What AI is and examples of how it is used in legalWhat AI is and examples of how it is used in legal
What AI is and examples of how it is used in legalBen Gardner
 

En vedette (20)

The State of Streaming Analytics: The Need for Speed and Scale
The State of Streaming Analytics: The Need for Speed and ScaleThe State of Streaming Analytics: The Need for Speed and Scale
The State of Streaming Analytics: The Need for Speed and Scale
 
Why And How To Leverage Predictive APIs In Any Application
Why And How To Leverage Predictive APIs In Any Application Why And How To Leverage Predictive APIs In Any Application
Why And How To Leverage Predictive APIs In Any Application
 
Semantic Computing Executive Briefing
Semantic Computing Executive Briefing Semantic Computing Executive Briefing
Semantic Computing Executive Briefing
 
Machine Learning Intro Session
Machine Learning Intro SessionMachine Learning Intro Session
Machine Learning Intro Session
 
Intro to modelling-supervised learning
Intro to modelling-supervised learningIntro to modelling-supervised learning
Intro to modelling-supervised learning
 
Lecture 02 introduction to ai
Lecture 02 introduction to aiLecture 02 introduction to ai
Lecture 02 introduction to ai
 
Machine learning intro
Machine learning introMachine learning intro
Machine learning intro
 
Intro to Machine Learning
Intro to Machine LearningIntro to Machine Learning
Intro to Machine Learning
 
Basics of Machine Learning
Basics of Machine LearningBasics of Machine Learning
Basics of Machine Learning
 
Machine learning
Machine learningMachine learning
Machine learning
 
Evaluating Big Data Predictive Analytics Platforms
Evaluating Big Data Predictive Analytics PlatformsEvaluating Big Data Predictive Analytics Platforms
Evaluating Big Data Predictive Analytics Platforms
 
Commercializing legal AI research: lessons learned
Commercializing legal AI research: lessons learnedCommercializing legal AI research: lessons learned
Commercializing legal AI research: lessons learned
 
An Intuitive Intro To Machine Learning
An Intuitive Intro To Machine LearningAn Intuitive Intro To Machine Learning
An Intuitive Intro To Machine Learning
 
AI in legal practice – the research perspective
AI in legal practice – the research perspectiveAI in legal practice – the research perspective
AI in legal practice – the research perspective
 
Basics of Machine Learning
Basics of Machine LearningBasics of Machine Learning
Basics of Machine Learning
 
Artificial intelligence
Artificial intelligenceArtificial intelligence
Artificial intelligence
 
Introduction to AI
Introduction to AIIntroduction to AI
Introduction to AI
 
An introduction to AI (artificial intelligence)
An introduction to AI (artificial intelligence)An introduction to AI (artificial intelligence)
An introduction to AI (artificial intelligence)
 
Machine learning basics using trees algorithm (Random forest, Gradient Boosting)
Machine learning basics using trees algorithm (Random forest, Gradient Boosting)Machine learning basics using trees algorithm (Random forest, Gradient Boosting)
Machine learning basics using trees algorithm (Random forest, Gradient Boosting)
 
What AI is and examples of how it is used in legal
What AI is and examples of how it is used in legalWhat AI is and examples of how it is used in legal
What AI is and examples of how it is used in legal
 

Similaire à Intro to machine learning for web folks @ BlendWebMix

Time-to-Event Models, presented by DataSong and Revolution Analytics
Time-to-Event Models, presented by DataSong and Revolution AnalyticsTime-to-Event Models, presented by DataSong and Revolution Analytics
Time-to-Event Models, presented by DataSong and Revolution AnalyticsRevolution Analytics
 
Fairness and Privacy in AI/ML Systems
Fairness and Privacy in AI/ML SystemsFairness and Privacy in AI/ML Systems
Fairness and Privacy in AI/ML SystemsKrishnaram Kenthapadi
 
Barga Galvanize Sept 2015
Barga Galvanize Sept 2015Barga Galvanize Sept 2015
Barga Galvanize Sept 2015Roger Barga
 
Einstein Analytics Prediction Builder
Einstein Analytics Prediction BuilderEinstein Analytics Prediction Builder
Einstein Analytics Prediction Builderrikkehovgaard
 
Operationalizing Customer Analytics with Azure and Power BI
Operationalizing Customer Analytics with Azure and Power BIOperationalizing Customer Analytics with Azure and Power BI
Operationalizing Customer Analytics with Azure and Power BICCG
 
Intro to Data Analytics with Oscar's Director of Product
 Intro to Data Analytics with Oscar's Director of Product Intro to Data Analytics with Oscar's Director of Product
Intro to Data Analytics with Oscar's Director of ProductProduct School
 
Recruiting Metrics That Really Work For You | Talent Connect San Francisco 2014
Recruiting Metrics That Really Work For You | Talent Connect San Francisco 2014Recruiting Metrics That Really Work For You | Talent Connect San Francisco 2014
Recruiting Metrics That Really Work For You | Talent Connect San Francisco 2014LinkedIn Talent Solutions
 
HWZ-Darden Konferenz: Building a Sustainable Analytics Orientation
HWZ-Darden Konferenz: Building a Sustainable Analytics OrientationHWZ-Darden Konferenz: Building a Sustainable Analytics Orientation
HWZ-Darden Konferenz: Building a Sustainable Analytics OrientationHWZ Hochschule für Wirtschaft
 
Machine Learning and Remarketing
Machine Learning and RemarketingMachine Learning and Remarketing
Machine Learning and RemarketingClark Boyd
 
Designing Outcomes For Usability Nycupa Hurst Final
Designing Outcomes For Usability Nycupa Hurst FinalDesigning Outcomes For Usability Nycupa Hurst Final
Designing Outcomes For Usability Nycupa Hurst FinalWIKOLO
 
Rd big data & analytics v1.0
Rd big data & analytics v1.0Rd big data & analytics v1.0
Rd big data & analytics v1.0Yadu Balehosur
 
Metrics to Maturity, Intelligence for Innovation: Your Value Proposition
Metrics to Maturity, Intelligence for Innovation: Your Value PropositionMetrics to Maturity, Intelligence for Innovation: Your Value Proposition
Metrics to Maturity, Intelligence for Innovation: Your Value PropositionCherwell Software
 
What MBA Students Need to Know about CX, Data Science and Surveys
What MBA Students Need to Know about CX, Data Science and SurveysWhat MBA Students Need to Know about CX, Data Science and Surveys
What MBA Students Need to Know about CX, Data Science and SurveysBusiness Over Broadway
 
Data Analysis - Making Big Data Work
Data Analysis - Making Big Data WorkData Analysis - Making Big Data Work
Data Analysis - Making Big Data WorkDavid Chiu
 
Maxdiff webinar_10_19_10
 Maxdiff webinar_10_19_10 Maxdiff webinar_10_19_10
Maxdiff webinar_10_19_10QuestionPro
 
Lean Analytics & Analytics Dashboards
Lean Analytics & Analytics DashboardsLean Analytics & Analytics Dashboards
Lean Analytics & Analytics DashboardsYves Ferket
 

Similaire à Intro to machine learning for web folks @ BlendWebMix (20)

Time-to-Event Models, presented by DataSong and Revolution Analytics
Time-to-Event Models, presented by DataSong and Revolution AnalyticsTime-to-Event Models, presented by DataSong and Revolution Analytics
Time-to-Event Models, presented by DataSong and Revolution Analytics
 
Fairness and Privacy in AI/ML Systems
Fairness and Privacy in AI/ML SystemsFairness and Privacy in AI/ML Systems
Fairness and Privacy in AI/ML Systems
 
Barga Galvanize Sept 2015
Barga Galvanize Sept 2015Barga Galvanize Sept 2015
Barga Galvanize Sept 2015
 
Projects
ProjectsProjects
Projects
 
Machine learning
Machine learningMachine learning
Machine learning
 
Einstein Analytics Prediction Builder
Einstein Analytics Prediction BuilderEinstein Analytics Prediction Builder
Einstein Analytics Prediction Builder
 
Operationalizing Customer Analytics with Azure and Power BI
Operationalizing Customer Analytics with Azure and Power BIOperationalizing Customer Analytics with Azure and Power BI
Operationalizing Customer Analytics with Azure and Power BI
 
Intro to Data Analytics with Oscar's Director of Product
 Intro to Data Analytics with Oscar's Director of Product Intro to Data Analytics with Oscar's Director of Product
Intro to Data Analytics with Oscar's Director of Product
 
Recruiting Metrics That Really Work For You | Talent Connect San Francisco 2014
Recruiting Metrics That Really Work For You | Talent Connect San Francisco 2014Recruiting Metrics That Really Work For You | Talent Connect San Francisco 2014
Recruiting Metrics That Really Work For You | Talent Connect San Francisco 2014
 
HWZ-Darden Konferenz: Building a Sustainable Analytics Orientation
HWZ-Darden Konferenz: Building a Sustainable Analytics OrientationHWZ-Darden Konferenz: Building a Sustainable Analytics Orientation
HWZ-Darden Konferenz: Building a Sustainable Analytics Orientation
 
Machine Learning and Remarketing
Machine Learning and RemarketingMachine Learning and Remarketing
Machine Learning and Remarketing
 
Designing Outcomes For Usability Nycupa Hurst Final
Designing Outcomes For Usability Nycupa Hurst FinalDesigning Outcomes For Usability Nycupa Hurst Final
Designing Outcomes For Usability Nycupa Hurst Final
 
Analytics in the Cloud
Analytics in the CloudAnalytics in the Cloud
Analytics in the Cloud
 
Rd big data & analytics v1.0
Rd big data & analytics v1.0Rd big data & analytics v1.0
Rd big data & analytics v1.0
 
Metrics to Maturity, Intelligence for Innovation: Your Value Proposition
Metrics to Maturity, Intelligence for Innovation: Your Value PropositionMetrics to Maturity, Intelligence for Innovation: Your Value Proposition
Metrics to Maturity, Intelligence for Innovation: Your Value Proposition
 
What MBA Students Need to Know about CX, Data Science and Surveys
What MBA Students Need to Know about CX, Data Science and SurveysWhat MBA Students Need to Know about CX, Data Science and Surveys
What MBA Students Need to Know about CX, Data Science and Surveys
 
Data Analysis - Making Big Data Work
Data Analysis - Making Big Data WorkData Analysis - Making Big Data Work
Data Analysis - Making Big Data Work
 
PQF Overview
PQF OverviewPQF Overview
PQF Overview
 
Maxdiff webinar_10_19_10
 Maxdiff webinar_10_19_10 Maxdiff webinar_10_19_10
Maxdiff webinar_10_19_10
 
Lean Analytics & Analytics Dashboards
Lean Analytics & Analytics DashboardsLean Analytics & Analytics Dashboards
Lean Analytics & Analytics Dashboards
 

Plus de Louis Dorard

From Data to Artificial Intelligence with the Machine Learning Canvas — ODSC ...
From Data to Artificial Intelligence with the Machine Learning Canvas — ODSC ...From Data to Artificial Intelligence with the Machine Learning Canvas — ODSC ...
From Data to Artificial Intelligence with the Machine Learning Canvas — ODSC ...Louis Dorard
 
From Data to AI with the Machine Learning Canvas
From Data to AI with the Machine Learning CanvasFrom Data to AI with the Machine Learning Canvas
From Data to AI with the Machine Learning CanvasLouis Dorard
 
Trusting AI with important decisions
Trusting AI with important decisionsTrusting AI with important decisions
Trusting AI with important decisionsLouis Dorard
 
Data Summit Brussels: Introduction
Data Summit Brussels: IntroductionData Summit Brussels: Introduction
Data Summit Brussels: IntroductionLouis Dorard
 
Exploration & Exploitation Challenge 2011
Exploration & Exploitation Challenge 2011Exploration & Exploitation Challenge 2011
Exploration & Exploitation Challenge 2011Louis Dorard
 

Plus de Louis Dorard (6)

From Data to Artificial Intelligence with the Machine Learning Canvas — ODSC ...
From Data to Artificial Intelligence with the Machine Learning Canvas — ODSC ...From Data to Artificial Intelligence with the Machine Learning Canvas — ODSC ...
From Data to Artificial Intelligence with the Machine Learning Canvas — ODSC ...
 
From Data to AI with the Machine Learning Canvas
From Data to AI with the Machine Learning CanvasFrom Data to AI with the Machine Learning Canvas
From Data to AI with the Machine Learning Canvas
 
Trusting AI with important decisions
Trusting AI with important decisionsTrusting AI with important decisions
Trusting AI with important decisions
 
Data Summit Brussels: Introduction
Data Summit Brussels: IntroductionData Summit Brussels: Introduction
Data Summit Brussels: Introduction
 
Big Data 2.0
Big Data 2.0Big Data 2.0
Big Data 2.0
 
Exploration & Exploitation Challenge 2011
Exploration & Exploitation Challenge 2011Exploration & Exploitation Challenge 2011
Exploration & Exploitation Challenge 2011
 

Dernier

Connector Corner: Extending LLM automation use cases with UiPath GenAI connec...
Connector Corner: Extending LLM automation use cases with UiPath GenAI connec...Connector Corner: Extending LLM automation use cases with UiPath GenAI connec...
Connector Corner: Extending LLM automation use cases with UiPath GenAI connec...DianaGray10
 
Artificial Intelligence & SEO Trends for 2024
Artificial Intelligence & SEO Trends for 2024Artificial Intelligence & SEO Trends for 2024
Artificial Intelligence & SEO Trends for 2024D Cloud Solutions
 
Meet the new FSP 3000 M-Flex800™
Meet the new FSP 3000 M-Flex800™Meet the new FSP 3000 M-Flex800™
Meet the new FSP 3000 M-Flex800™Adtran
 
UiPath Solutions Management Preview - Northern CA Chapter - March 22.pdf
UiPath Solutions Management Preview - Northern CA Chapter - March 22.pdfUiPath Solutions Management Preview - Northern CA Chapter - March 22.pdf
UiPath Solutions Management Preview - Northern CA Chapter - March 22.pdfDianaGray10
 
UWB Technology for Enhanced Indoor and Outdoor Positioning in Physiological M...
UWB Technology for Enhanced Indoor and Outdoor Positioning in Physiological M...UWB Technology for Enhanced Indoor and Outdoor Positioning in Physiological M...
UWB Technology for Enhanced Indoor and Outdoor Positioning in Physiological M...UbiTrack UK
 
Cybersecurity Workshop #1.pptx
Cybersecurity Workshop #1.pptxCybersecurity Workshop #1.pptx
Cybersecurity Workshop #1.pptxGDSC PJATK
 
Comparing Sidecar-less Service Mesh from Cilium and Istio
Comparing Sidecar-less Service Mesh from Cilium and IstioComparing Sidecar-less Service Mesh from Cilium and Istio
Comparing Sidecar-less Service Mesh from Cilium and IstioChristian Posta
 
COMPUTER 10 Lesson 8 - Building a Website
COMPUTER 10 Lesson 8 - Building a WebsiteCOMPUTER 10 Lesson 8 - Building a Website
COMPUTER 10 Lesson 8 - Building a Websitedgelyza
 
VoIP Service and Marketing using Odoo and Asterisk PBX
VoIP Service and Marketing using Odoo and Asterisk PBXVoIP Service and Marketing using Odoo and Asterisk PBX
VoIP Service and Marketing using Odoo and Asterisk PBXTarek Kalaji
 
9 Steps For Building Winning Founding Team
9 Steps For Building Winning Founding Team9 Steps For Building Winning Founding Team
9 Steps For Building Winning Founding TeamAdam Moalla
 
Designing A Time bound resource download URL
Designing A Time bound resource download URLDesigning A Time bound resource download URL
Designing A Time bound resource download URLRuncy Oommen
 
How Accurate are Carbon Emissions Projections?
How Accurate are Carbon Emissions Projections?How Accurate are Carbon Emissions Projections?
How Accurate are Carbon Emissions Projections?IES VE
 
Basic Building Blocks of Internet of Things.
Basic Building Blocks of Internet of Things.Basic Building Blocks of Internet of Things.
Basic Building Blocks of Internet of Things.YounusS2
 
Crea il tuo assistente AI con lo Stregatto (open source python framework)
Crea il tuo assistente AI con lo Stregatto (open source python framework)Crea il tuo assistente AI con lo Stregatto (open source python framework)
Crea il tuo assistente AI con lo Stregatto (open source python framework)Commit University
 
activity_diagram_combine_v4_20190827.pdfactivity_diagram_combine_v4_20190827.pdf
activity_diagram_combine_v4_20190827.pdfactivity_diagram_combine_v4_20190827.pdfactivity_diagram_combine_v4_20190827.pdfactivity_diagram_combine_v4_20190827.pdf
activity_diagram_combine_v4_20190827.pdfactivity_diagram_combine_v4_20190827.pdfJamie (Taka) Wang
 
Building AI-Driven Apps Using Semantic Kernel.pptx
Building AI-Driven Apps Using Semantic Kernel.pptxBuilding AI-Driven Apps Using Semantic Kernel.pptx
Building AI-Driven Apps Using Semantic Kernel.pptxUdaiappa Ramachandran
 
Using IESVE for Loads, Sizing and Heat Pump Modeling to Achieve Decarbonization
Using IESVE for Loads, Sizing and Heat Pump Modeling to Achieve DecarbonizationUsing IESVE for Loads, Sizing and Heat Pump Modeling to Achieve Decarbonization
Using IESVE for Loads, Sizing and Heat Pump Modeling to Achieve DecarbonizationIES VE
 
UiPath Platform: The Backend Engine Powering Your Automation - Session 1
UiPath Platform: The Backend Engine Powering Your Automation - Session 1UiPath Platform: The Backend Engine Powering Your Automation - Session 1
UiPath Platform: The Backend Engine Powering Your Automation - Session 1DianaGray10
 

Dernier (20)

Connector Corner: Extending LLM automation use cases with UiPath GenAI connec...
Connector Corner: Extending LLM automation use cases with UiPath GenAI connec...Connector Corner: Extending LLM automation use cases with UiPath GenAI connec...
Connector Corner: Extending LLM automation use cases with UiPath GenAI connec...
 
Artificial Intelligence & SEO Trends for 2024
Artificial Intelligence & SEO Trends for 2024Artificial Intelligence & SEO Trends for 2024
Artificial Intelligence & SEO Trends for 2024
 
Meet the new FSP 3000 M-Flex800™
Meet the new FSP 3000 M-Flex800™Meet the new FSP 3000 M-Flex800™
Meet the new FSP 3000 M-Flex800™
 
20150722 - AGV
20150722 - AGV20150722 - AGV
20150722 - AGV
 
UiPath Solutions Management Preview - Northern CA Chapter - March 22.pdf
UiPath Solutions Management Preview - Northern CA Chapter - March 22.pdfUiPath Solutions Management Preview - Northern CA Chapter - March 22.pdf
UiPath Solutions Management Preview - Northern CA Chapter - March 22.pdf
 
UWB Technology for Enhanced Indoor and Outdoor Positioning in Physiological M...
UWB Technology for Enhanced Indoor and Outdoor Positioning in Physiological M...UWB Technology for Enhanced Indoor and Outdoor Positioning in Physiological M...
UWB Technology for Enhanced Indoor and Outdoor Positioning in Physiological M...
 
Cybersecurity Workshop #1.pptx
Cybersecurity Workshop #1.pptxCybersecurity Workshop #1.pptx
Cybersecurity Workshop #1.pptx
 
Comparing Sidecar-less Service Mesh from Cilium and Istio
Comparing Sidecar-less Service Mesh from Cilium and IstioComparing Sidecar-less Service Mesh from Cilium and Istio
Comparing Sidecar-less Service Mesh from Cilium and Istio
 
201610817 - edge part1
201610817 - edge part1201610817 - edge part1
201610817 - edge part1
 
COMPUTER 10 Lesson 8 - Building a Website
COMPUTER 10 Lesson 8 - Building a WebsiteCOMPUTER 10 Lesson 8 - Building a Website
COMPUTER 10 Lesson 8 - Building a Website
 
VoIP Service and Marketing using Odoo and Asterisk PBX
VoIP Service and Marketing using Odoo and Asterisk PBXVoIP Service and Marketing using Odoo and Asterisk PBX
VoIP Service and Marketing using Odoo and Asterisk PBX
 
9 Steps For Building Winning Founding Team
9 Steps For Building Winning Founding Team9 Steps For Building Winning Founding Team
9 Steps For Building Winning Founding Team
 
Designing A Time bound resource download URL
Designing A Time bound resource download URLDesigning A Time bound resource download URL
Designing A Time bound resource download URL
 
How Accurate are Carbon Emissions Projections?
How Accurate are Carbon Emissions Projections?How Accurate are Carbon Emissions Projections?
How Accurate are Carbon Emissions Projections?
 
Basic Building Blocks of Internet of Things.
Basic Building Blocks of Internet of Things.Basic Building Blocks of Internet of Things.
Basic Building Blocks of Internet of Things.
 
Crea il tuo assistente AI con lo Stregatto (open source python framework)
Crea il tuo assistente AI con lo Stregatto (open source python framework)Crea il tuo assistente AI con lo Stregatto (open source python framework)
Crea il tuo assistente AI con lo Stregatto (open source python framework)
 
activity_diagram_combine_v4_20190827.pdfactivity_diagram_combine_v4_20190827.pdf
activity_diagram_combine_v4_20190827.pdfactivity_diagram_combine_v4_20190827.pdfactivity_diagram_combine_v4_20190827.pdfactivity_diagram_combine_v4_20190827.pdf
activity_diagram_combine_v4_20190827.pdfactivity_diagram_combine_v4_20190827.pdf
 
Building AI-Driven Apps Using Semantic Kernel.pptx
Building AI-Driven Apps Using Semantic Kernel.pptxBuilding AI-Driven Apps Using Semantic Kernel.pptx
Building AI-Driven Apps Using Semantic Kernel.pptx
 
Using IESVE for Loads, Sizing and Heat Pump Modeling to Achieve Decarbonization
Using IESVE for Loads, Sizing and Heat Pump Modeling to Achieve DecarbonizationUsing IESVE for Loads, Sizing and Heat Pump Modeling to Achieve Decarbonization
Using IESVE for Loads, Sizing and Heat Pump Modeling to Achieve Decarbonization
 
UiPath Platform: The Backend Engine Powering Your Automation - Session 1
UiPath Platform: The Backend Engine Powering Your Automation - Session 1UiPath Platform: The Backend Engine Powering Your Automation - Session 1
UiPath Platform: The Backend Engine Powering Your Automation - Session 1
 

Intro to machine learning for web folks @ BlendWebMix

  • 1. Intro to Machine Learning
 for web folks “Machine Learning, je m’y mets dès demain” @louisdorard #blendwebmix 2015
  • 2. –Mike Gualtieri, Principal Analyst at Forrester “Predictive apps are the next big thing in app development.”
  • 4. –Waqar Hasan, VISA “Predictive is the ‘killer app’ for big data.”
  • 5. Amazon for David Jones (@d_jones, see source)
  • 6. Amazon for David Jones (@d_jones, see source)
  • 9. –Charles Parker, PhD, Allston Trading “ML isn’t about ML”
  • 14. “Where makers of Predictive APIs and apps meet”
  • 15. Machine Learning Use cases Limitations Modern tools Case study ML Canvas
  • 18. “Which type of email is this? — Spam/Ham” 

  • 19. “Which type of email is this? — Spam/Ham” 
 Classification
  • 20. I O “Which type of email is this? — Spam/Ham” 

  • 21. ??
  • 23. “How much is this house worth? — X $” 
 -> Regression
  • 24. Bedrooms Bathrooms Surface (foot²) Year built Type Price ($) 3 1 860 1950 house 565,000 3 1 1012 1951 house 2 1.5 968 1976 townhouse 447,000 4 1315 1950 house 648,000 3 2 1599 1964 house 3 2 987 1951 townhouse 790,000 1 1 530 2007 condo 122,000 4 2 1574 1964 house 835,000 4 2001 house 855,000 3 2.5 1472 2005 house 4 3.5 1714 2005 townhouse 2 2 1113 1999 condo 1 769 1999 condo 315,000
  • 25. Bedrooms Bathrooms Surface (foot²) Year built Type Price ($) 3 1 860 1950 house 565,000 3 1 1012 1951 house 2 1.5 968 1976 townhouse 447,000 4 1315 1950 house 648,000 3 2 1599 1964 house 3 2 987 1951 townhouse 790,000 1 1 530 2007 condo 122,000 4 2 1574 1964 house 835,000 4 2001 house 855,000 3 2.5 1472 2005 house 4 3.5 1714 2005 townhouse 2 2 1113 1999 condo 1 769 1999 condo 315,000
  • 27. ML is a set of AI techniques where “intelligence” is built by referring to examples
  • 30. • Real-estate • Spam • Priority inbox • Crowd prediction property price email spam indicator email importance indicator location & context #people Zillow Gmail Gmail Tranquilien
  • 31. I. Get more customers • Reduce churn • Score leads • Optimize campaigns customer churn indicator customer revenue customer & campaign interest indicator
  • 32. II. Serve customers better • Cross-sell • Increase engagement • Optimize pricing customer & product purchase indicator user & item interest indicator product & price #sales
  • 33. III. Serve customers more efficiently • Predict demand • Automate tasks • Use predictive enterprise apps context demand credit application repayment indicator
  • 34. Predictive enterprise apps • Priority filtering • Message routing • Auto-configuration message priority indicator request employee user & actions settings RULES
  • 35. –Katherine Barr, Partner at VC-firm MDV "Pairing human workers with machine learning and automation will transform knowledge work and unleash new levels of human productivity and creativity."
  • 41. Need examples of inputs AND outputs
  • 43. What if not enough data points?
  • 45. What if similar inputs have dissimilar outputs?
  • 47. Bedrooms Bathrooms Price ($) 3 2 500,000 3 2 800,000 1 1 300,000 1 1 800,000
  • 48. Bedrooms Bathrooms Surface (foot²) Year built Price ($) 3 2 800 1950 500,000 3 2 1000 1950 800,000 1 1 500 1950 300,000 1 1 500 2014 800,000
  • 49. • Need examples of inputs AND outputs • Need enough examples • Need enough“features”
  • 50. –@louisdorard “A model can only be as good as the data it was given to train on”
  • 51. –McKinsey & Co. (2011) “A significant constraint on realizing value from big data will be a shortage of talent, particularly of people with deep expertise in statistics and machine learning.”
  • 52. MLaaS & Predictive APIs:
 ML for all
  • 54. HTML / CSS / JavaScript
  • 55. HTML / CSS / JavaScript
  • 59. The two phases of machine learning: • TRAIN a model • PREDICT with a model
  • 60. The two methods of predictive APIs: • TRAIN a model • PREDICT with a model
  • 61. The two methods of predictive APIs: • model = create_model(dataset) • predicted_output = create_prediction(model, new_input)
  • 62. The two methods of predictive APIs: • model = create_model(‘training.csv’) • predicted_output = create_prediction(model, new_input)
  • 66. From Large to Small & Medium Enterprises • recommendations in e-commerce • => 71% increase in revenue • churn detection • => 11% increase in retention
  • 72. • Who: SaaS company selling monthly subscription • Question asked:“Is this customer going to leave within 1 month?” • Input: customer • Output: no-churn or churn • Data collection: history up until 1 month ago • Baseline: if no usage for more than 15 days then churn
  • 73. Learning: OK but • How to represent customers? • What to do after predicting churn?
  • 74. Customer representation: • basic info (age, income, etc.) • usage of service (# times used app, avg time spent, features used, etc.) • interactions with customer support (how many, topics of questions, satisfaction ratings)
  • 75. Taking action to prevent churn: • contact customers (in which order?) • switch to different plan • give special offer • no action?
  • 76. Measuring accuracy: • #TP (we predict customer churns and he does) • #FP (we predict customer churns but he doesn’t) • #FN (we predict customer doesn’t churn but he does) • Compare to heuristic/baseline
  • 77. Return On Investment: • Taking action for each TP (and FP) has a cost • For each TP we“gain”:
 (success rate of action) * (revenue /cust. /month) • Imagine… • perfect predictions • revenue /cust. /month = 10€ • success rate of action = 20% • cost of action = 2€ • Which ROI?
  • 80. PREDICTIONS OBJECTIVES DATA Context Who will use the predictive system / who will be affected by it? Provide some background. Value Proposition What are we trying to do? E.g. spend less time on X, increase Y... Data Sources Where do/can we get data from? (internal database, 3rd party API, etc.) Problem Question to predict answers to (in plain English) Input (i.e. question "parameter") Possible outputs (i.e. "answers") Type of problem (e.g. classification, regression, recommendation...) Baseline What is an alternative way of making predictions (e.g. manual rules based on feature values)? Performance evaluation Domain-specific / bottom-line metrics for monitoring performance in production Prediction accuracy metrics (e.g. MSE if regression; % accuracy, #FP for classification) Offline performance evaluation method (e.g. cross-validation or simple training/test split) Dataset How do we collect data (inputs and outputs)? How many data points? Features Used to represent inputs and extracted from data sources above. Group by types and mention key features if too many to list all. Using predictions When do we make predictions and how many? What is the time constraint for making those predictions? How do we use predictions and confidence values? Learning predictive models When do we create/update models? With which data / how much? What is the time constraint for creating a model? Criteria for deploying model (e.g. minimum performance value — absolute, relative to baseline or to previous model) IDEASPECSDEPLOYMENT
  • 83. PREDICTIONS OBJECTIVES DATA BACKGROUND End-user Value prop Sources ENGINE SPECS ML problem Perf eval Preparation INTEGRATION Using pred Learning modelINTEGRATION Using pred Learning model
  • 84. Why fill in ML canvas? • Target the right problem for your company • Choose right algorithm, infrastructure, or ML solution • Guide project management • Improve team communication
  • 86. Recap
  • 87. • ML to create value from data • 2 phases: TRAIN and PREDICT • MLaaS & Predictive APIs make it more accessible • Good data is essential • What do we do with predictions? • Accuracy is not the objective! A/B test? • Start with the ML Canvas • Later: deploy, maintain, improve…