SlideShare ist ein Scribd-Unternehmen logo
1 von 48
Downloaden Sie, um offline zu lesen
10MoreLessons
Learned from building real-life Machine Learning Systems
Xavier Amatriain (@xamat) 10/13/2015
Machine Learning
@Quora
Our Mission
“To share and grow the world’s knowledge”
● Millions of questions & answers
● Millions of users
● Thousands of topics
● ...
Demand
What we care about
Quality
Relevance
Lots of data relations
ML Applications @ Quora
● Answer ranking
● Feed ranking
● Topic recommendations
● User recommendations
● Email digest
● Ask2Answer
● Duplicate Questions
● Related Questions
● Spam/moderation
● Trending now
● ...
Models
● Logistic Regression
● Elastic Nets
● Gradient Boosted Decision
Trees
● Random Forests
● (Deep) Neural Networks
● LambdaMART
● Matrix Factorization
● LDA
● ...
10MoreLessons
Learned from implementing real-life ML systems
1.Implicitsignalsbeat
explicitones
(almostalways)
Implicit vs. Explicit
● Many have acknowledged
that implicit feedback is more useful
● Is implicit feedback really always
more useful?
● If so, why?
● Implicit data is (usually):
○ More dense, and available for all users
○ Better representative of user behavior vs.
user reflection
○ More related to final objective function
○ Better correlated with AB test results
● E.g. Rating vs watching
Implicit vs. Explicit
● However
○ It is not always the case that
direct implicit feedback correlates
well with long-term retention
○ E.g. clickbait
● Solution:
○ Combine different forms of
implicit + explicit to better represent
long-term goal
Implicit vs. Explicit
2.YourModelwilllearn
whatyouteachittolearn
Training a model
● Model will learn according to:
○ Training data (e.g. implicit and explicit)
○ Target function (e.g. probability of user reading an answer)
○ Metric (e.g. precision vs. recall)
● Example 1 (made up):
○ Optimize probability of a user going to the cinema to
watch a movie and rate it “highly” by using purchase history
and previous ratings. Use NDCG of the ranking as final
metric using only movies rated 4 or higher as positives.
Example 2 - Quora’s feed
● Training data = implicit + explicit
● Target function: Value of showing a story to a
user ~ weighted sum of actions: v = ∑a
va
1{ya
= 1}
○ predict probabilities for each action, then compute expected
value: v_pred = E[ V | x ] = ∑a
va
p(a | x)
● Metric: any ranking metric
3.Supervisedvs.plus
UnsupervisedLearning
Supervised/Unsupervised Learning
● Unsupervised learning as dimensionality reduction
● Unsupervised learning as feature engineering
● The “magic” behind combining
unsupervised/supervised learning
○ E.g.1 clustering + knn
○ E.g.2 Matrix Factorization
■ MF can be interpreted as
● Unsupervised:
○ Dimensionality Reduction a la PCA
○ Clustering (e.g. NMF)
● Supervised
○ Labeled targets ~ regression
Supervised/Unsupervised Learning
● One of the “tricks” in Deep Learning is how it
combines unsupervised/supervised learning
○ E.g. Stacked Autoencoders
○ E.g. training of convolutional nets
4.Everythingisanensemble
Ensembles
● Netflix Prize was won by an ensemble
○ Initially Bellkor was using GDBTs
○ BigChaos introduced ANN-based ensemble
● Most practical applications of ML run an ensemble
○ Why wouldn’t you?
○ At least as good as the best of your methods
○ Can add completely different approaches (e.
g. CF and content-based)
○ You can use many different models at the
ensemble layer: LR, GDBTs, RFs, ANNs...
Ensembles & Feature Engineering
● Ensembles are the way to turn any model into a feature!
● E.g. Don’t know if the way to go is to use Factorization
Machines, Tensor Factorization, or RNNs?
○ Treat each model as a “feature”
○ Feed them into an ensemble
The Master Algorithm?
It definitely is an ensemble!
5.Theoutputofyourmodel
willbetheinputofanotherone
(andotherdesignproblems)
Outputs will be inputs
● Ensembles turn any model into a feature
○ That’s great!
○ That can be a mess!
● Make sure the output of your model is ready to
accept data dependencies
○ E.g. can you easily change the distribution of the
value without affecting all other models
depending on it?
● Avoid feedback loops
● Can you treat your ML infrastructure as you would
your software one?
ML vs Software
● Can you treat your ML infrastructure as you would
your software one?
○ Yes and No
● You should apply best Software Engineering
practices (e.g. encapsulation, abstraction, cohesion,
low coupling…)
● However, Design Patterns for Machine Learning
software are not well known/documented
6.Thepains&gains
ofFeatureEngineering
Feature Engineering
● Main properties of a well-behaved ML feature
○ Reusable
○ Transformable
○ Interpretable
○ Reliable
● Reusability: You should be able to reuse features in different
models, applications, and teams
● Transformability: Besides directly reusing a feature, it
should be easy to use a transformation of it (e.g. log(f), max(f),
∑ft
over a time window…)
Feature Engineering
● Main properties of a well-behaved ML feature
○ Reusable
○ Transformable
○ Interpretable
○ Reliable
● Interpretability: In order to do any of the previous, you
need to be able to understand the meaning of features and
interpret their values.
● Reliability: It should be easy to monitor and detect bugs/issues
in features
Feature Engineering Example - Quora Answer Ranking
What is a good Quora answer?
• truthful
• reusable
• provides explanation
• well formatted
• ...
Feature Engineering Example - Quora Answer Ranking
How are those dimensions translated
into features?
• Features that relate to the answer
quality itself
• Interaction features
(upvotes/downvotes, clicks,
comments…)
• User features (e.g. expertise in topic)
7.Thetwofacesofyour
MLinfrastructure
Machine Learning Infrastructure
● Whenever you develop any ML infrastructure, you need to
target two different modes:
○ Mode 1: ML experimentation
■ Flexibility
■ Easy-to-use
■ Reusability
○ Mode 2: ML production
■ All of the above + performance & scalability
● Ideally you want the two modes to be as similar as possible
● How to combine them?
Machine Learning Infrastructure: Experimentation & Production
● Option 1:
○ Favor experimentation and only invest in productionizing
once something shows results
○ E.g. Have ML researchers use R and then ask Engineers
to implement things in production when they work
● Option 2:
○ Favor production and have “researchers” struggle to figure
out how to run experiments
○ E.g. Implement highly optimized C++ code and have ML
researchers experiment only through data available in logs/DB
Machine Learning Infrastructure: Experimentation & Production
● Option 1:
○ Favor experimentation and only invest in productionazing once
something shows results
○ E.g. Have ML researchers use R and then ask Engineers to
implement things in production when they work
● Option 2:
○ Favor production and have “researchers” struggle to figure out
how to run experiments
○ E.g. Implement highly optimized C++ code and have ML
researchers experiment only through data available in logs/DB
● Good intermediate options:
○ Have ML “researchers” experiment on iPython Notebooks using
Python tools (scikit-learn, Theano…). Use same tools in
production whenever possible, implement optimized versions
only when needed.
○ Implement abstraction layers on top of optimized
implementations so they can be accessed from regular/friendly
experimentation tools
Machine Learning Infrastructure: Experimentation & Production
8.Whyyoushouldcareabout
answeringquestions(aboutyourmodel)
Model debuggability
● Value of a model = value it brings to the product
● Product owners/stakeholders have expectations on
the product
● It is important to answer questions to why did
something fail
● Bridge gap between product design and ML algos
● Model debuggability is so important it can
determine:
○ Particular model to use
○ Features to rely on
○ Implementation of tools
Model debuggability
● E.g. Why am I seeing or not seeing
this on my homepage feed?
9.Youdon’tneedtodistribute
yourMLalgorithm
Distributing ML
● Most of what people do in practice can fit into a multi-
core machine
○ Smart data sampling
○ Offline schemes
○ Efficient parallel code
● Dangers of “easy” distributed approaches such
as Hadoop/Spark
● Do you care about costs? How about latencies?
Distributing ML
● Example of optimizing computations to fit them into
one machine
○ Spark implementation: 6 hours, 15 machines
○ Developer time: 4 days
○ C++ implementation: 10 minutes, 1 machine
● Most practical applications of Big Data can fit into
a (multicore) implementation
10.Theuntoldstoryof
DataScienceandvs.MLengineering
Data Scientists and ML Engineers
● We all know the definition of a Data Scientist
● Where do Data Scientists fit in an organization?
○ Many companies struggling with this
● Valuable to have strong DS who can bring value
from the data
● Strong DS with solid engineering skills are
unicorns and finding them is not scalable
○ DS need engineers to bring things to production
○ Engineers have enough on their plate to be willing to
“productionize” cool DS projects
The data-driven ML innovation funnel
Data Research
ML Exploration -
Product Design
AB Testing
Data Scientists and ML Engineers
● Solution:
○ (1) Define different parts of the innovation funnel
■ Part 1. Data research & hypothesis
building -> Data Science
■ Part 2. ML solution building &
implementation -> ML Engineering
■ Part 3. Online experimentation, AB
Testing analysis-> Data Science
○ (2) Broaden the definition of ML Engineers
to include from coding experts with high-level
ML knowledge to ML experts with good
software skills
Data Research
ML Solution
AB Testing
Data
Science
Data
Science
ML
Engineering
Conclusions
● Make sure you teach your model what you
want it to learn
● Ensembles and the combination of
supervised/unsupervised techniques are key
in many ML applications
● Important to focus on feature engineering
● Be thoughtful about
○ your ML infrastructure/tools
○ about organizing your teams
10 more lessons learned from building Machine Learning systems - MLConf

Weitere ähnliche Inhalte

Was ist angesagt?

Artificial Intelligence (Current state and future of A.I) by Mudasir Khushk
Artificial Intelligence (Current state and future of A.I) by Mudasir KhushkArtificial Intelligence (Current state and future of A.I) by Mudasir Khushk
Artificial Intelligence (Current state and future of A.I) by Mudasir KhushkMudsaraliKhushik
 
What is Artificial Intelligence | Artificial Intelligence Tutorial For Beginn...
What is Artificial Intelligence | Artificial Intelligence Tutorial For Beginn...What is Artificial Intelligence | Artificial Intelligence Tutorial For Beginn...
What is Artificial Intelligence | Artificial Intelligence Tutorial For Beginn...Edureka!
 
Artificial Intelligence and Machine Learning
Artificial Intelligence and Machine LearningArtificial Intelligence and Machine Learning
Artificial Intelligence and Machine LearningMykola Dobrochynskyy
 
Ai in e commerce (public)
Ai in e commerce (public)Ai in e commerce (public)
Ai in e commerce (public)Michael Lesniak
 
The Five Levels of Generative AI for Games
The Five Levels of Generative AI for GamesThe Five Levels of Generative AI for Games
The Five Levels of Generative AI for GamesJon Radoff
 
Conversational AI and Chatbot Integrations
Conversational AI and Chatbot IntegrationsConversational AI and Chatbot Integrations
Conversational AI and Chatbot IntegrationsCristina Vidu
 
generative-ai-fundamentals and Large language models
generative-ai-fundamentals and Large language modelsgenerative-ai-fundamentals and Large language models
generative-ai-fundamentals and Large language modelsAdventureWorld5
 
Augmented intelligence is new way forward !
Augmented intelligence is new way forward ! Augmented intelligence is new way forward !
Augmented intelligence is new way forward ! Steve Ardire
 
Understanding generative AI models A comprehensive overview.pdf
Understanding generative AI models A comprehensive overview.pdfUnderstanding generative AI models A comprehensive overview.pdf
Understanding generative AI models A comprehensive overview.pdfStephenAmell4
 
Introduction To Artificial Intelligence PowerPoint Presentation Slides
Introduction To Artificial Intelligence PowerPoint Presentation SlidesIntroduction To Artificial Intelligence PowerPoint Presentation Slides
Introduction To Artificial Intelligence PowerPoint Presentation SlidesSlideTeam
 
Artificial intelligence
Artificial intelligenceArtificial intelligence
Artificial intelligenceA.I. Tazib
 
Using the power of Generative AI at scale
Using the power of Generative AI at scaleUsing the power of Generative AI at scale
Using the power of Generative AI at scaleMaxim Salnikov
 
AI Everywhere: How Microsoft is Democratizing AI
AI Everywhere: How Microsoft is Democratizing AIAI Everywhere: How Microsoft is Democratizing AI
AI Everywhere: How Microsoft is Democratizing AIPaul Prae
 

Was ist angesagt? (20)

Artificial Intelligence (Current state and future of A.I) by Mudasir Khushk
Artificial Intelligence (Current state and future of A.I) by Mudasir KhushkArtificial Intelligence (Current state and future of A.I) by Mudasir Khushk
Artificial Intelligence (Current state and future of A.I) by Mudasir Khushk
 
What is Artificial Intelligence | Artificial Intelligence Tutorial For Beginn...
What is Artificial Intelligence | Artificial Intelligence Tutorial For Beginn...What is Artificial Intelligence | Artificial Intelligence Tutorial For Beginn...
What is Artificial Intelligence | Artificial Intelligence Tutorial For Beginn...
 
Implementing Ethics in AI
Implementing Ethics in AIImplementing Ethics in AI
Implementing Ethics in AI
 
Artificial intelligence
Artificial intelligenceArtificial intelligence
Artificial intelligence
 
Artificial Intelligence and Machine Learning
Artificial Intelligence and Machine LearningArtificial Intelligence and Machine Learning
Artificial Intelligence and Machine Learning
 
Ai in e commerce (public)
Ai in e commerce (public)Ai in e commerce (public)
Ai in e commerce (public)
 
The Five Levels of Generative AI for Games
The Five Levels of Generative AI for GamesThe Five Levels of Generative AI for Games
The Five Levels of Generative AI for Games
 
Conversational AI and Chatbot Integrations
Conversational AI and Chatbot IntegrationsConversational AI and Chatbot Integrations
Conversational AI and Chatbot Integrations
 
The Ethics of AI
The Ethics of AIThe Ethics of AI
The Ethics of AI
 
AI as a service
AI as a serviceAI as a service
AI as a service
 
generative-ai-fundamentals and Large language models
generative-ai-fundamentals and Large language modelsgenerative-ai-fundamentals and Large language models
generative-ai-fundamentals and Large language models
 
Augmented intelligence is new way forward !
Augmented intelligence is new way forward ! Augmented intelligence is new way forward !
Augmented intelligence is new way forward !
 
Understanding generative AI models A comprehensive overview.pdf
Understanding generative AI models A comprehensive overview.pdfUnderstanding generative AI models A comprehensive overview.pdf
Understanding generative AI models A comprehensive overview.pdf
 
Introduction To Artificial Intelligence PowerPoint Presentation Slides
Introduction To Artificial Intelligence PowerPoint Presentation SlidesIntroduction To Artificial Intelligence PowerPoint Presentation Slides
Introduction To Artificial Intelligence PowerPoint Presentation Slides
 
Artificial Intelligence
Artificial IntelligenceArtificial Intelligence
Artificial Intelligence
 
Artificial Intelligence
Artificial IntelligenceArtificial Intelligence
Artificial Intelligence
 
Artificial intelligence
Artificial intelligenceArtificial intelligence
Artificial intelligence
 
How Siri Works
How Siri WorksHow Siri Works
How Siri Works
 
Using the power of Generative AI at scale
Using the power of Generative AI at scaleUsing the power of Generative AI at scale
Using the power of Generative AI at scale
 
AI Everywhere: How Microsoft is Democratizing AI
AI Everywhere: How Microsoft is Democratizing AIAI Everywhere: How Microsoft is Democratizing AI
AI Everywhere: How Microsoft is Democratizing AI
 

Ähnlich wie 10 more lessons learned from building Machine Learning systems - MLConf

Strata 2016 - Lessons Learned from building real-life Machine Learning Systems
Strata 2016 -  Lessons Learned from building real-life Machine Learning SystemsStrata 2016 -  Lessons Learned from building real-life Machine Learning Systems
Strata 2016 - Lessons Learned from building real-life Machine Learning SystemsXavier Amatriain
 
Scaling Recommendations at Quora (RecSys talk 9/16/2016)
Scaling Recommendations at Quora (RecSys talk 9/16/2016)Scaling Recommendations at Quora (RecSys talk 9/16/2016)
Scaling Recommendations at Quora (RecSys talk 9/16/2016)Nikhil Dandekar
 
BIG2016- Lessons Learned from building real-life user-focused Big Data systems
BIG2016- Lessons Learned from building real-life user-focused Big Data systemsBIG2016- Lessons Learned from building real-life user-focused Big Data systems
BIG2016- Lessons Learned from building real-life user-focused Big Data systemsXavier Amatriain
 
Recsys 2016 tutorial: Lessons learned from building real-life recommender sys...
Recsys 2016 tutorial: Lessons learned from building real-life recommender sys...Recsys 2016 tutorial: Lessons learned from building real-life recommender sys...
Recsys 2016 tutorial: Lessons learned from building real-life recommender sys...Xavier Amatriain
 
Staying Shallow & Lean in a Deep Learning World
Staying Shallow & Lean in a Deep Learning WorldStaying Shallow & Lean in a Deep Learning World
Staying Shallow & Lean in a Deep Learning WorldXavier Amatriain
 
AI hype or reality
AI  hype or realityAI  hype or reality
AI hype or realityAwantik Das
 
General introduction to AI ML DL DS
General introduction to AI ML DL DSGeneral introduction to AI ML DL DS
General introduction to AI ML DL DSRoopesh Kohad
 
Production-Ready BIG ML Workflows - from zero to hero
Production-Ready BIG ML Workflows - from zero to heroProduction-Ready BIG ML Workflows - from zero to hero
Production-Ready BIG ML Workflows - from zero to heroDaniel Marcous
 
Machine Learning: Artificial Intelligence isn't just a Science Fiction topic
Machine Learning: Artificial Intelligence isn't just a Science Fiction topicMachine Learning: Artificial Intelligence isn't just a Science Fiction topic
Machine Learning: Artificial Intelligence isn't just a Science Fiction topicRaúl Garreta
 
Machine Learning: Inteligencia Artificial no es sólo un tema de Ciencia Ficci...
Machine Learning: Inteligencia Artificial no es sólo un tema de Ciencia Ficci...Machine Learning: Inteligencia Artificial no es sólo un tema de Ciencia Ficci...
Machine Learning: Inteligencia Artificial no es sólo un tema de Ciencia Ficci....NET Conf UY
 
ML Platform Q1 Meetup: Airbnb's End-to-End Machine Learning Infrastructure
ML Platform Q1 Meetup: Airbnb's End-to-End Machine Learning InfrastructureML Platform Q1 Meetup: Airbnb's End-to-End Machine Learning Infrastructure
ML Platform Q1 Meetup: Airbnb's End-to-End Machine Learning InfrastructureFei Chen
 
Day 2 (Lecture 5): A Practitioner's Perspective on Building Machine Product i...
Day 2 (Lecture 5): A Practitioner's Perspective on Building Machine Product i...Day 2 (Lecture 5): A Practitioner's Perspective on Building Machine Product i...
Day 2 (Lecture 5): A Practitioner's Perspective on Building Machine Product i...Aseda Owusua Addai-Deseh
 
Open source ml systems that need to be built
Open source ml systems that need to be builtOpen source ml systems that need to be built
Open source ml systems that need to be builtNikhil Garg
 
Nikhil Garg, Engineering Manager, Quora at MLconf SF 2016
Nikhil Garg, Engineering Manager, Quora at MLconf SF 2016Nikhil Garg, Engineering Manager, Quora at MLconf SF 2016
Nikhil Garg, Engineering Manager, Quora at MLconf SF 2016MLconf
 
Building A Machine Learning Platform At Quora (1)
Building A Machine Learning Platform At Quora (1)Building A Machine Learning Platform At Quora (1)
Building A Machine Learning Platform At Quora (1)Nikhil Garg
 
Prototyping Workshop - Wireframes, Mockups, Prototypes
Prototyping Workshop - Wireframes, Mockups, PrototypesPrototyping Workshop - Wireframes, Mockups, Prototypes
Prototyping Workshop - Wireframes, Mockups, PrototypesMarta Soncodi
 
Apache Cassandra Lunch #54: Machine Learning with Spark + Cassandra Part 2
Apache Cassandra Lunch #54: Machine Learning with Spark + Cassandra Part 2Apache Cassandra Lunch #54: Machine Learning with Spark + Cassandra Part 2
Apache Cassandra Lunch #54: Machine Learning with Spark + Cassandra Part 2Anant Corporation
 

Ähnlich wie 10 more lessons learned from building Machine Learning systems - MLConf (20)

Strata 2016 - Lessons Learned from building real-life Machine Learning Systems
Strata 2016 -  Lessons Learned from building real-life Machine Learning SystemsStrata 2016 -  Lessons Learned from building real-life Machine Learning Systems
Strata 2016 - Lessons Learned from building real-life Machine Learning Systems
 
Scaling Recommendations at Quora (RecSys talk 9/16/2016)
Scaling Recommendations at Quora (RecSys talk 9/16/2016)Scaling Recommendations at Quora (RecSys talk 9/16/2016)
Scaling Recommendations at Quora (RecSys talk 9/16/2016)
 
BIG2016- Lessons Learned from building real-life user-focused Big Data systems
BIG2016- Lessons Learned from building real-life user-focused Big Data systemsBIG2016- Lessons Learned from building real-life user-focused Big Data systems
BIG2016- Lessons Learned from building real-life user-focused Big Data systems
 
Recsys 2016 tutorial: Lessons learned from building real-life recommender sys...
Recsys 2016 tutorial: Lessons learned from building real-life recommender sys...Recsys 2016 tutorial: Lessons learned from building real-life recommender sys...
Recsys 2016 tutorial: Lessons learned from building real-life recommender sys...
 
Staying Shallow & Lean in a Deep Learning World
Staying Shallow & Lean in a Deep Learning WorldStaying Shallow & Lean in a Deep Learning World
Staying Shallow & Lean in a Deep Learning World
 
AI hype or reality
AI  hype or realityAI  hype or reality
AI hype or reality
 
General introduction to AI ML DL DS
General introduction to AI ML DL DSGeneral introduction to AI ML DL DS
General introduction to AI ML DL DS
 
Production-Ready BIG ML Workflows - from zero to hero
Production-Ready BIG ML Workflows - from zero to heroProduction-Ready BIG ML Workflows - from zero to hero
Production-Ready BIG ML Workflows - from zero to hero
 
Machine Learning: Artificial Intelligence isn't just a Science Fiction topic
Machine Learning: Artificial Intelligence isn't just a Science Fiction topicMachine Learning: Artificial Intelligence isn't just a Science Fiction topic
Machine Learning: Artificial Intelligence isn't just a Science Fiction topic
 
L15.pptx
L15.pptxL15.pptx
L15.pptx
 
Machine Learning: Inteligencia Artificial no es sólo un tema de Ciencia Ficci...
Machine Learning: Inteligencia Artificial no es sólo un tema de Ciencia Ficci...Machine Learning: Inteligencia Artificial no es sólo un tema de Ciencia Ficci...
Machine Learning: Inteligencia Artificial no es sólo un tema de Ciencia Ficci...
 
ML Platform Q1 Meetup: Airbnb's End-to-End Machine Learning Infrastructure
ML Platform Q1 Meetup: Airbnb's End-to-End Machine Learning InfrastructureML Platform Q1 Meetup: Airbnb's End-to-End Machine Learning Infrastructure
ML Platform Q1 Meetup: Airbnb's End-to-End Machine Learning Infrastructure
 
Day 2 (Lecture 5): A Practitioner's Perspective on Building Machine Product i...
Day 2 (Lecture 5): A Practitioner's Perspective on Building Machine Product i...Day 2 (Lecture 5): A Practitioner's Perspective on Building Machine Product i...
Day 2 (Lecture 5): A Practitioner's Perspective on Building Machine Product i...
 
Open source ml systems that need to be built
Open source ml systems that need to be builtOpen source ml systems that need to be built
Open source ml systems that need to be built
 
Nikhil Garg, Engineering Manager, Quora at MLconf SF 2016
Nikhil Garg, Engineering Manager, Quora at MLconf SF 2016Nikhil Garg, Engineering Manager, Quora at MLconf SF 2016
Nikhil Garg, Engineering Manager, Quora at MLconf SF 2016
 
Building A Machine Learning Platform At Quora (1)
Building A Machine Learning Platform At Quora (1)Building A Machine Learning Platform At Quora (1)
Building A Machine Learning Platform At Quora (1)
 
Prototyping Workshop - Wireframes, Mockups, Prototypes
Prototyping Workshop - Wireframes, Mockups, PrototypesPrototyping Workshop - Wireframes, Mockups, Prototypes
Prototyping Workshop - Wireframes, Mockups, Prototypes
 
Data science
Data scienceData science
Data science
 
Apache Cassandra Lunch #54: Machine Learning with Spark + Cassandra Part 2
Apache Cassandra Lunch #54: Machine Learning with Spark + Cassandra Part 2Apache Cassandra Lunch #54: Machine Learning with Spark + Cassandra Part 2
Apache Cassandra Lunch #54: Machine Learning with Spark + Cassandra Part 2
 
Persian MNIST in 5 Minutes
Persian MNIST in 5 MinutesPersian MNIST in 5 Minutes
Persian MNIST in 5 Minutes
 

Mehr von Xavier Amatriain

Data/AI driven product development: from video streaming to telehealth
Data/AI driven product development: from video streaming to telehealthData/AI driven product development: from video streaming to telehealth
Data/AI driven product development: from video streaming to telehealthXavier Amatriain
 
AI-driven product innovation: from Recommender Systems to COVID-19
AI-driven product innovation: from Recommender Systems to COVID-19AI-driven product innovation: from Recommender Systems to COVID-19
AI-driven product innovation: from Recommender Systems to COVID-19Xavier Amatriain
 
AI for COVID-19 - Q42020 update
AI for COVID-19 - Q42020 updateAI for COVID-19 - Q42020 update
AI for COVID-19 - Q42020 updateXavier Amatriain
 
AI for COVID-19: An online virtual care approach
AI for COVID-19: An online virtual care approachAI for COVID-19: An online virtual care approach
AI for COVID-19: An online virtual care approachXavier Amatriain
 
Lessons learned from building practical deep learning systems
Lessons learned from building practical deep learning systemsLessons learned from building practical deep learning systems
Lessons learned from building practical deep learning systemsXavier Amatriain
 
AI for healthcare: Scaling Access and Quality of Care for Everyone
AI for healthcare: Scaling Access and Quality of Care for EveryoneAI for healthcare: Scaling Access and Quality of Care for Everyone
AI for healthcare: Scaling Access and Quality of Care for EveryoneXavier Amatriain
 
Towards online universal quality healthcare through AI
Towards online universal quality healthcare through AITowards online universal quality healthcare through AI
Towards online universal quality healthcare through AIXavier Amatriain
 
From one to zero: Going smaller as a growth strategy
From one to zero: Going smaller as a growth strategyFrom one to zero: Going smaller as a growth strategy
From one to zero: Going smaller as a growth strategyXavier Amatriain
 
Learning to speak medicine
Learning to speak medicineLearning to speak medicine
Learning to speak medicineXavier Amatriain
 
Recommender Systems In Industry
Recommender Systems In IndustryRecommender Systems In Industry
Recommender Systems In IndustryXavier Amatriain
 
Medical advice as a Recommender System
Medical advice as a Recommender SystemMedical advice as a Recommender System
Medical advice as a Recommender SystemXavier Amatriain
 
Past present and future of Recommender Systems: an Industry Perspective
Past present and future of Recommender Systems: an Industry PerspectivePast present and future of Recommender Systems: an Industry Perspective
Past present and future of Recommender Systems: an Industry PerspectiveXavier Amatriain
 
Machine Learning for Q&A Sites: The Quora Example
Machine Learning for Q&A Sites: The Quora ExampleMachine Learning for Q&A Sites: The Quora Example
Machine Learning for Q&A Sites: The Quora ExampleXavier Amatriain
 
Past, present, and future of Recommender Systems: an industry perspective
Past, present, and future of Recommender Systems: an industry perspectivePast, present, and future of Recommender Systems: an industry perspective
Past, present, and future of Recommender Systems: an industry perspectiveXavier Amatriain
 
Barcelona ML Meetup - Lessons Learned
Barcelona ML Meetup - Lessons LearnedBarcelona ML Meetup - Lessons Learned
Barcelona ML Meetup - Lessons LearnedXavier Amatriain
 
10 more lessons learned from building Machine Learning systems
10 more lessons learned from building Machine Learning systems10 more lessons learned from building Machine Learning systems
10 more lessons learned from building Machine Learning systemsXavier Amatriain
 
Machine Learning to Grow the World's Knowledge
Machine Learning to Grow  the World's KnowledgeMachine Learning to Grow  the World's Knowledge
Machine Learning to Grow the World's KnowledgeXavier Amatriain
 
MLConf Seattle 2015 - ML@Quora
MLConf Seattle 2015 - ML@QuoraMLConf Seattle 2015 - ML@Quora
MLConf Seattle 2015 - ML@QuoraXavier Amatriain
 
Lean DevOps - Lessons Learned from Innovation-driven Companies
Lean DevOps - Lessons Learned from Innovation-driven CompaniesLean DevOps - Lessons Learned from Innovation-driven Companies
Lean DevOps - Lessons Learned from Innovation-driven CompaniesXavier Amatriain
 

Mehr von Xavier Amatriain (20)

Data/AI driven product development: from video streaming to telehealth
Data/AI driven product development: from video streaming to telehealthData/AI driven product development: from video streaming to telehealth
Data/AI driven product development: from video streaming to telehealth
 
AI-driven product innovation: from Recommender Systems to COVID-19
AI-driven product innovation: from Recommender Systems to COVID-19AI-driven product innovation: from Recommender Systems to COVID-19
AI-driven product innovation: from Recommender Systems to COVID-19
 
AI for COVID-19 - Q42020 update
AI for COVID-19 - Q42020 updateAI for COVID-19 - Q42020 update
AI for COVID-19 - Q42020 update
 
AI for COVID-19: An online virtual care approach
AI for COVID-19: An online virtual care approachAI for COVID-19: An online virtual care approach
AI for COVID-19: An online virtual care approach
 
Lessons learned from building practical deep learning systems
Lessons learned from building practical deep learning systemsLessons learned from building practical deep learning systems
Lessons learned from building practical deep learning systems
 
AI for healthcare: Scaling Access and Quality of Care for Everyone
AI for healthcare: Scaling Access and Quality of Care for EveryoneAI for healthcare: Scaling Access and Quality of Care for Everyone
AI for healthcare: Scaling Access and Quality of Care for Everyone
 
Towards online universal quality healthcare through AI
Towards online universal quality healthcare through AITowards online universal quality healthcare through AI
Towards online universal quality healthcare through AI
 
From one to zero: Going smaller as a growth strategy
From one to zero: Going smaller as a growth strategyFrom one to zero: Going smaller as a growth strategy
From one to zero: Going smaller as a growth strategy
 
Learning to speak medicine
Learning to speak medicineLearning to speak medicine
Learning to speak medicine
 
ML to cure the world
ML to cure the worldML to cure the world
ML to cure the world
 
Recommender Systems In Industry
Recommender Systems In IndustryRecommender Systems In Industry
Recommender Systems In Industry
 
Medical advice as a Recommender System
Medical advice as a Recommender SystemMedical advice as a Recommender System
Medical advice as a Recommender System
 
Past present and future of Recommender Systems: an Industry Perspective
Past present and future of Recommender Systems: an Industry PerspectivePast present and future of Recommender Systems: an Industry Perspective
Past present and future of Recommender Systems: an Industry Perspective
 
Machine Learning for Q&A Sites: The Quora Example
Machine Learning for Q&A Sites: The Quora ExampleMachine Learning for Q&A Sites: The Quora Example
Machine Learning for Q&A Sites: The Quora Example
 
Past, present, and future of Recommender Systems: an industry perspective
Past, present, and future of Recommender Systems: an industry perspectivePast, present, and future of Recommender Systems: an industry perspective
Past, present, and future of Recommender Systems: an industry perspective
 
Barcelona ML Meetup - Lessons Learned
Barcelona ML Meetup - Lessons LearnedBarcelona ML Meetup - Lessons Learned
Barcelona ML Meetup - Lessons Learned
 
10 more lessons learned from building Machine Learning systems
10 more lessons learned from building Machine Learning systems10 more lessons learned from building Machine Learning systems
10 more lessons learned from building Machine Learning systems
 
Machine Learning to Grow the World's Knowledge
Machine Learning to Grow  the World's KnowledgeMachine Learning to Grow  the World's Knowledge
Machine Learning to Grow the World's Knowledge
 
MLConf Seattle 2015 - ML@Quora
MLConf Seattle 2015 - ML@QuoraMLConf Seattle 2015 - ML@Quora
MLConf Seattle 2015 - ML@Quora
 
Lean DevOps - Lessons Learned from Innovation-driven Companies
Lean DevOps - Lessons Learned from Innovation-driven CompaniesLean DevOps - Lessons Learned from Innovation-driven Companies
Lean DevOps - Lessons Learned from Innovation-driven Companies
 

Kürzlich hochgeladen

EPE3163_Hydro power stations_Unit2_Lect2.pptx
EPE3163_Hydro power stations_Unit2_Lect2.pptxEPE3163_Hydro power stations_Unit2_Lect2.pptx
EPE3163_Hydro power stations_Unit2_Lect2.pptxJoseeMusabyimana
 
nvidia AI-gtc 2024 partial slide deck.pptx
nvidia AI-gtc 2024 partial slide deck.pptxnvidia AI-gtc 2024 partial slide deck.pptx
nvidia AI-gtc 2024 partial slide deck.pptxjasonsedano2
 
Popular-NO1 Kala Jadu Expert Specialist In Germany Kala Jadu Expert Specialis...
Popular-NO1 Kala Jadu Expert Specialist In Germany Kala Jadu Expert Specialis...Popular-NO1 Kala Jadu Expert Specialist In Germany Kala Jadu Expert Specialis...
Popular-NO1 Kala Jadu Expert Specialist In Germany Kala Jadu Expert Specialis...Amil baba
 
GENERAL CONDITIONS FOR CONTRACTS OF CIVIL ENGINEERING WORKS
GENERAL CONDITIONS  FOR  CONTRACTS OF CIVIL ENGINEERING WORKS GENERAL CONDITIONS  FOR  CONTRACTS OF CIVIL ENGINEERING WORKS
GENERAL CONDITIONS FOR CONTRACTS OF CIVIL ENGINEERING WORKS Bahzad5
 
Renewable Energy & Entrepreneurship Workshop_21Feb2024.pdf
Renewable Energy & Entrepreneurship Workshop_21Feb2024.pdfRenewable Energy & Entrepreneurship Workshop_21Feb2024.pdf
Renewable Energy & Entrepreneurship Workshop_21Feb2024.pdfodunowoeminence2019
 
Test of Significance of Large Samples for Mean = µ.pptx
Test of Significance of Large Samples for Mean = µ.pptxTest of Significance of Large Samples for Mean = µ.pptx
Test of Significance of Large Samples for Mean = µ.pptxHome
 
cloud computing notes for anna university syllabus
cloud computing notes for anna university syllabuscloud computing notes for anna university syllabus
cloud computing notes for anna university syllabusViolet Violet
 
Basic Principle of Electrochemical Sensor
Basic Principle of  Electrochemical SensorBasic Principle of  Electrochemical Sensor
Basic Principle of Electrochemical SensorTanvir Moin
 
Semiconductor Physics Background and Light Emitting Diode(LEDs)-.pptx
Semiconductor Physics Background and Light Emitting Diode(LEDs)-.pptxSemiconductor Physics Background and Light Emitting Diode(LEDs)-.pptx
Semiconductor Physics Background and Light Emitting Diode(LEDs)-.pptxbhoomijyani51
 
Lecture 1: Basics of trigonometry (surveying)
Lecture 1: Basics of trigonometry (surveying)Lecture 1: Basics of trigonometry (surveying)
Lecture 1: Basics of trigonometry (surveying)Bahzad5
 
OS Services, System call, Virtual Machine
OS Services, System call, Virtual MachineOS Services, System call, Virtual Machine
OS Services, System call, Virtual MachineDivya S
 
دليل تجارب الاسفلت المختبرية - Asphalt Experiments Guide Laboratory
دليل تجارب الاسفلت المختبرية - Asphalt Experiments Guide Laboratoryدليل تجارب الاسفلت المختبرية - Asphalt Experiments Guide Laboratory
دليل تجارب الاسفلت المختبرية - Asphalt Experiments Guide LaboratoryBahzad5
 
A Seminar on Electric Vehicle Software Simulation
A Seminar on Electric Vehicle Software SimulationA Seminar on Electric Vehicle Software Simulation
A Seminar on Electric Vehicle Software SimulationMohsinKhanA
 
Transforming Process Safety Management: Challenges, Benefits, and Transition ...
Transforming Process Safety Management: Challenges, Benefits, and Transition ...Transforming Process Safety Management: Challenges, Benefits, and Transition ...
Transforming Process Safety Management: Challenges, Benefits, and Transition ...soginsider
 
Vertical- Machining - Center - VMC -LMW-Machine-Tool-Division.pptx
Vertical- Machining - Center - VMC -LMW-Machine-Tool-Division.pptxVertical- Machining - Center - VMC -LMW-Machine-Tool-Division.pptx
Vertical- Machining - Center - VMC -LMW-Machine-Tool-Division.pptxLMW Machine Tool Division
 
Technology Features of Apollo HDD Machine, Its Technical Specification with C...
Technology Features of Apollo HDD Machine, Its Technical Specification with C...Technology Features of Apollo HDD Machine, Its Technical Specification with C...
Technology Features of Apollo HDD Machine, Its Technical Specification with C...Apollo Techno Industries Pvt Ltd
 
Modelling Guide for Timber Structures - FPInnovations
Modelling Guide for Timber Structures - FPInnovationsModelling Guide for Timber Structures - FPInnovations
Modelling Guide for Timber Structures - FPInnovationsYusuf Yıldız
 

Kürzlich hochgeladen (20)

EPE3163_Hydro power stations_Unit2_Lect2.pptx
EPE3163_Hydro power stations_Unit2_Lect2.pptxEPE3163_Hydro power stations_Unit2_Lect2.pptx
EPE3163_Hydro power stations_Unit2_Lect2.pptx
 
nvidia AI-gtc 2024 partial slide deck.pptx
nvidia AI-gtc 2024 partial slide deck.pptxnvidia AI-gtc 2024 partial slide deck.pptx
nvidia AI-gtc 2024 partial slide deck.pptx
 
Présentation IIRB 2024 Chloe Dufrane.pdf
Présentation IIRB 2024 Chloe Dufrane.pdfPrésentation IIRB 2024 Chloe Dufrane.pdf
Présentation IIRB 2024 Chloe Dufrane.pdf
 
Popular-NO1 Kala Jadu Expert Specialist In Germany Kala Jadu Expert Specialis...
Popular-NO1 Kala Jadu Expert Specialist In Germany Kala Jadu Expert Specialis...Popular-NO1 Kala Jadu Expert Specialist In Germany Kala Jadu Expert Specialis...
Popular-NO1 Kala Jadu Expert Specialist In Germany Kala Jadu Expert Specialis...
 
GENERAL CONDITIONS FOR CONTRACTS OF CIVIL ENGINEERING WORKS
GENERAL CONDITIONS  FOR  CONTRACTS OF CIVIL ENGINEERING WORKS GENERAL CONDITIONS  FOR  CONTRACTS OF CIVIL ENGINEERING WORKS
GENERAL CONDITIONS FOR CONTRACTS OF CIVIL ENGINEERING WORKS
 
Renewable Energy & Entrepreneurship Workshop_21Feb2024.pdf
Renewable Energy & Entrepreneurship Workshop_21Feb2024.pdfRenewable Energy & Entrepreneurship Workshop_21Feb2024.pdf
Renewable Energy & Entrepreneurship Workshop_21Feb2024.pdf
 
Test of Significance of Large Samples for Mean = µ.pptx
Test of Significance of Large Samples for Mean = µ.pptxTest of Significance of Large Samples for Mean = µ.pptx
Test of Significance of Large Samples for Mean = µ.pptx
 
cloud computing notes for anna university syllabus
cloud computing notes for anna university syllabuscloud computing notes for anna university syllabus
cloud computing notes for anna university syllabus
 
Basic Principle of Electrochemical Sensor
Basic Principle of  Electrochemical SensorBasic Principle of  Electrochemical Sensor
Basic Principle of Electrochemical Sensor
 
Semiconductor Physics Background and Light Emitting Diode(LEDs)-.pptx
Semiconductor Physics Background and Light Emitting Diode(LEDs)-.pptxSemiconductor Physics Background and Light Emitting Diode(LEDs)-.pptx
Semiconductor Physics Background and Light Emitting Diode(LEDs)-.pptx
 
Lecture 1: Basics of trigonometry (surveying)
Lecture 1: Basics of trigonometry (surveying)Lecture 1: Basics of trigonometry (surveying)
Lecture 1: Basics of trigonometry (surveying)
 
OS Services, System call, Virtual Machine
OS Services, System call, Virtual MachineOS Services, System call, Virtual Machine
OS Services, System call, Virtual Machine
 
دليل تجارب الاسفلت المختبرية - Asphalt Experiments Guide Laboratory
دليل تجارب الاسفلت المختبرية - Asphalt Experiments Guide Laboratoryدليل تجارب الاسفلت المختبرية - Asphalt Experiments Guide Laboratory
دليل تجارب الاسفلت المختبرية - Asphalt Experiments Guide Laboratory
 
A Seminar on Electric Vehicle Software Simulation
A Seminar on Electric Vehicle Software SimulationA Seminar on Electric Vehicle Software Simulation
A Seminar on Electric Vehicle Software Simulation
 
Transforming Process Safety Management: Challenges, Benefits, and Transition ...
Transforming Process Safety Management: Challenges, Benefits, and Transition ...Transforming Process Safety Management: Challenges, Benefits, and Transition ...
Transforming Process Safety Management: Challenges, Benefits, and Transition ...
 
Vertical- Machining - Center - VMC -LMW-Machine-Tool-Division.pptx
Vertical- Machining - Center - VMC -LMW-Machine-Tool-Division.pptxVertical- Machining - Center - VMC -LMW-Machine-Tool-Division.pptx
Vertical- Machining - Center - VMC -LMW-Machine-Tool-Division.pptx
 
Technology Features of Apollo HDD Machine, Its Technical Specification with C...
Technology Features of Apollo HDD Machine, Its Technical Specification with C...Technology Features of Apollo HDD Machine, Its Technical Specification with C...
Technology Features of Apollo HDD Machine, Its Technical Specification with C...
 
Modelling Guide for Timber Structures - FPInnovations
Modelling Guide for Timber Structures - FPInnovationsModelling Guide for Timber Structures - FPInnovations
Modelling Guide for Timber Structures - FPInnovations
 
Lecture 2 .pdf
Lecture 2                           .pdfLecture 2                           .pdf
Lecture 2 .pdf
 
Lecture 4 .pdf
Lecture 4                              .pdfLecture 4                              .pdf
Lecture 4 .pdf
 

10 more lessons learned from building Machine Learning systems - MLConf

  • 1. 10MoreLessons Learned from building real-life Machine Learning Systems Xavier Amatriain (@xamat) 10/13/2015
  • 3. Our Mission “To share and grow the world’s knowledge” ● Millions of questions & answers ● Millions of users ● Thousands of topics ● ...
  • 4. Demand What we care about Quality Relevance
  • 5. Lots of data relations
  • 6. ML Applications @ Quora ● Answer ranking ● Feed ranking ● Topic recommendations ● User recommendations ● Email digest ● Ask2Answer ● Duplicate Questions ● Related Questions ● Spam/moderation ● Trending now ● ...
  • 7. Models ● Logistic Regression ● Elastic Nets ● Gradient Boosted Decision Trees ● Random Forests ● (Deep) Neural Networks ● LambdaMART ● Matrix Factorization ● LDA ● ...
  • 10. Implicit vs. Explicit ● Many have acknowledged that implicit feedback is more useful ● Is implicit feedback really always more useful? ● If so, why?
  • 11. ● Implicit data is (usually): ○ More dense, and available for all users ○ Better representative of user behavior vs. user reflection ○ More related to final objective function ○ Better correlated with AB test results ● E.g. Rating vs watching Implicit vs. Explicit
  • 12. ● However ○ It is not always the case that direct implicit feedback correlates well with long-term retention ○ E.g. clickbait ● Solution: ○ Combine different forms of implicit + explicit to better represent long-term goal Implicit vs. Explicit
  • 14. Training a model ● Model will learn according to: ○ Training data (e.g. implicit and explicit) ○ Target function (e.g. probability of user reading an answer) ○ Metric (e.g. precision vs. recall) ● Example 1 (made up): ○ Optimize probability of a user going to the cinema to watch a movie and rate it “highly” by using purchase history and previous ratings. Use NDCG of the ranking as final metric using only movies rated 4 or higher as positives.
  • 15. Example 2 - Quora’s feed ● Training data = implicit + explicit ● Target function: Value of showing a story to a user ~ weighted sum of actions: v = ∑a va 1{ya = 1} ○ predict probabilities for each action, then compute expected value: v_pred = E[ V | x ] = ∑a va p(a | x) ● Metric: any ranking metric
  • 17. Supervised/Unsupervised Learning ● Unsupervised learning as dimensionality reduction ● Unsupervised learning as feature engineering ● The “magic” behind combining unsupervised/supervised learning ○ E.g.1 clustering + knn ○ E.g.2 Matrix Factorization ■ MF can be interpreted as ● Unsupervised: ○ Dimensionality Reduction a la PCA ○ Clustering (e.g. NMF) ● Supervised ○ Labeled targets ~ regression
  • 18. Supervised/Unsupervised Learning ● One of the “tricks” in Deep Learning is how it combines unsupervised/supervised learning ○ E.g. Stacked Autoencoders ○ E.g. training of convolutional nets
  • 20. Ensembles ● Netflix Prize was won by an ensemble ○ Initially Bellkor was using GDBTs ○ BigChaos introduced ANN-based ensemble ● Most practical applications of ML run an ensemble ○ Why wouldn’t you? ○ At least as good as the best of your methods ○ Can add completely different approaches (e. g. CF and content-based) ○ You can use many different models at the ensemble layer: LR, GDBTs, RFs, ANNs...
  • 21. Ensembles & Feature Engineering ● Ensembles are the way to turn any model into a feature! ● E.g. Don’t know if the way to go is to use Factorization Machines, Tensor Factorization, or RNNs? ○ Treat each model as a “feature” ○ Feed them into an ensemble
  • 22. The Master Algorithm? It definitely is an ensemble!
  • 24. Outputs will be inputs ● Ensembles turn any model into a feature ○ That’s great! ○ That can be a mess! ● Make sure the output of your model is ready to accept data dependencies ○ E.g. can you easily change the distribution of the value without affecting all other models depending on it? ● Avoid feedback loops ● Can you treat your ML infrastructure as you would your software one?
  • 25. ML vs Software ● Can you treat your ML infrastructure as you would your software one? ○ Yes and No ● You should apply best Software Engineering practices (e.g. encapsulation, abstraction, cohesion, low coupling…) ● However, Design Patterns for Machine Learning software are not well known/documented
  • 27. Feature Engineering ● Main properties of a well-behaved ML feature ○ Reusable ○ Transformable ○ Interpretable ○ Reliable ● Reusability: You should be able to reuse features in different models, applications, and teams ● Transformability: Besides directly reusing a feature, it should be easy to use a transformation of it (e.g. log(f), max(f), ∑ft over a time window…)
  • 28. Feature Engineering ● Main properties of a well-behaved ML feature ○ Reusable ○ Transformable ○ Interpretable ○ Reliable ● Interpretability: In order to do any of the previous, you need to be able to understand the meaning of features and interpret their values. ● Reliability: It should be easy to monitor and detect bugs/issues in features
  • 29. Feature Engineering Example - Quora Answer Ranking What is a good Quora answer? • truthful • reusable • provides explanation • well formatted • ...
  • 30. Feature Engineering Example - Quora Answer Ranking How are those dimensions translated into features? • Features that relate to the answer quality itself • Interaction features (upvotes/downvotes, clicks, comments…) • User features (e.g. expertise in topic)
  • 32. Machine Learning Infrastructure ● Whenever you develop any ML infrastructure, you need to target two different modes: ○ Mode 1: ML experimentation ■ Flexibility ■ Easy-to-use ■ Reusability ○ Mode 2: ML production ■ All of the above + performance & scalability ● Ideally you want the two modes to be as similar as possible ● How to combine them?
  • 33. Machine Learning Infrastructure: Experimentation & Production ● Option 1: ○ Favor experimentation and only invest in productionizing once something shows results ○ E.g. Have ML researchers use R and then ask Engineers to implement things in production when they work ● Option 2: ○ Favor production and have “researchers” struggle to figure out how to run experiments ○ E.g. Implement highly optimized C++ code and have ML researchers experiment only through data available in logs/DB
  • 34. Machine Learning Infrastructure: Experimentation & Production ● Option 1: ○ Favor experimentation and only invest in productionazing once something shows results ○ E.g. Have ML researchers use R and then ask Engineers to implement things in production when they work ● Option 2: ○ Favor production and have “researchers” struggle to figure out how to run experiments ○ E.g. Implement highly optimized C++ code and have ML researchers experiment only through data available in logs/DB
  • 35. ● Good intermediate options: ○ Have ML “researchers” experiment on iPython Notebooks using Python tools (scikit-learn, Theano…). Use same tools in production whenever possible, implement optimized versions only when needed. ○ Implement abstraction layers on top of optimized implementations so they can be accessed from regular/friendly experimentation tools Machine Learning Infrastructure: Experimentation & Production
  • 37. Model debuggability ● Value of a model = value it brings to the product ● Product owners/stakeholders have expectations on the product ● It is important to answer questions to why did something fail ● Bridge gap between product design and ML algos ● Model debuggability is so important it can determine: ○ Particular model to use ○ Features to rely on ○ Implementation of tools
  • 38. Model debuggability ● E.g. Why am I seeing or not seeing this on my homepage feed?
  • 40. Distributing ML ● Most of what people do in practice can fit into a multi- core machine ○ Smart data sampling ○ Offline schemes ○ Efficient parallel code ● Dangers of “easy” distributed approaches such as Hadoop/Spark ● Do you care about costs? How about latencies?
  • 41. Distributing ML ● Example of optimizing computations to fit them into one machine ○ Spark implementation: 6 hours, 15 machines ○ Developer time: 4 days ○ C++ implementation: 10 minutes, 1 machine ● Most practical applications of Big Data can fit into a (multicore) implementation
  • 43. Data Scientists and ML Engineers ● We all know the definition of a Data Scientist ● Where do Data Scientists fit in an organization? ○ Many companies struggling with this ● Valuable to have strong DS who can bring value from the data ● Strong DS with solid engineering skills are unicorns and finding them is not scalable ○ DS need engineers to bring things to production ○ Engineers have enough on their plate to be willing to “productionize” cool DS projects
  • 44. The data-driven ML innovation funnel Data Research ML Exploration - Product Design AB Testing
  • 45. Data Scientists and ML Engineers ● Solution: ○ (1) Define different parts of the innovation funnel ■ Part 1. Data research & hypothesis building -> Data Science ■ Part 2. ML solution building & implementation -> ML Engineering ■ Part 3. Online experimentation, AB Testing analysis-> Data Science ○ (2) Broaden the definition of ML Engineers to include from coding experts with high-level ML knowledge to ML experts with good software skills Data Research ML Solution AB Testing Data Science Data Science ML Engineering
  • 47. ● Make sure you teach your model what you want it to learn ● Ensembles and the combination of supervised/unsupervised techniques are key in many ML applications ● Important to focus on feature engineering ● Be thoughtful about ○ your ML infrastructure/tools ○ about organizing your teams