Machine Learning from a Product Perspective

Slide 1

Slide 1 text

MACHINE LEARNING FROM A PRODUCT PERSPECTIVE I N G A C H E N

Slide 2

Slide 2 text

@ I N G A C H E N S I L I C O N VA L L E Y N AT I V E D A U G H T E R O F S O F T WA R E + H A R D WA R E E N G I N E E R S I N V E S T M E N T B A N K E R T E C H M & A J E F F E R I E S S I L I C O N VA L L E Y E A R LY B U S I N E S S H I R E I o T S TA R T U P F O R C A R S A U T O M AT I C L A B S S A N F R A N C I S C O P R O D U C T M A N A G E R D ATA I N S I G H T S & F L E E T A U T O M AT I C L A B S S A N F R A N C I S C O P R O D U C T M A N A G E R A N A LY T I C S S Q U A R E S PA C E N E W YO R K C I T Y

Slide 3

Slide 3 text

Millions of miles of driving Millions of websites Slice of the internet Drivers Fuel eﬃciency Car Maintenance SMBs Online presence and business

Slide 4

Slide 4 text

Millions of miles of driving Millions of websites Slice of the internet Create an optimized experience for each user MACHINE LEARNING

Slide 5

Slide 5 text

B E YO N D T H E A L G O R I T H M : B U I L D I N G M L P R O D U C T S W H AT S H O U L D P R O D U C T P E O P L E B R I N G T O T H E TA B L E ? B A C KG R O U N D : W H AT I S M L? W H AT P R O B L E M S A R E G O O D F O R M L? W H Y N O W MACHINE LEARNING FROM A PRODUCT PERSPECTIVE

Slide 6

Slide 6 text

B E YO N D T H E A L G O R I T H M : B U I L D I N G M L P R O D U C T S W H AT P R O B L E M S A R E G O O D F O R M L? W H Y N O W MACHINE LEARNING FROM A PRODUCT PERSPECTIVE B A C KG R O U N D : W H AT I S M L? W H AT S H O U L D P R O D U C T P E O P L E B R I N G T O T H E TA B L E ?

Slide 7

Slide 7 text

Artificial Intelligence Human Intelligence Exhibited by Machines

Slide 8

Slide 8 text

GOALS OF AI: Reasoning Knowledge Planning Learning Natural Language Processing Perception Move & manipulate objects Artificial Intelligence Human Intelligence Exhibited by Machines

Slide 9

Slide 9 text

“[Machine Learning is the] ﬁeld of study that gives computers the ability to learn without being explicitly programmed Arthur Samuel, 1959

Slide 10

Slide 10 text

“[Machine Learning is the] ﬁeld of study that gives computers the ability to learn without being explicitly programmed (often more data than is humanly possible to go through) and makes a determination or prediction about something in the world. by observing data

Slide 11

Slide 11 text

H O W D O E S M A C H I N E L E A R N I N G W O R K ?

Slide 12

Slide 12 text

INPUT OUTPUT ML MODEL EMAIL SPAM NOT SPAM

Slide 13

Slide 13 text

DATA EMAILS

Slide 14

Slide 14 text

“CORRECT ANSWERS” IDEALLY…IT’S LABELED EMAILS LABELED AS SPAM / NOT SPAM

Slide 15

Slide 15 text

70% Training Set Validation Set 30% TEACHER GIVES EXAMPLES TO ILLUSTRATE A CONCEPT TEST

Slide 16

Slide 16 text

B E YO N D T H E A L G O R I T H M : B U I L D I N G M L P R O D U C T S B A C KG R O U N D : W H AT I S M L? W H AT P R O B L E M S A R E G O O D F O R M L? W H Y N O W MACHINE LEARNING FROM A PRODUCT PERSPECTIVE W H AT S H O U L D P R O D U C T P E O P L E B R I N G T O T H E TA B L E ?

Slide 17

Slide 17 text

D E C I S I O N S W I T H M A N Y I N P U T S and it’s unclear how to combine them W H AT P R O B L E M S A R E G O O D F O R M A C H I N E L E A R N I N G ?

Slide 18

Slide 18 text

W H O W I L L W I N T H E E L E C T I O N ? Hillary vs Trump Education Income level Race Gender Geographic location Religion What car you drive

Slide 19

Slide 19 text

No content

Slide 20

Slide 20 text

No content

Slide 21

Slide 21 text

D E C I S I O N S W I T H M A N Y O U T P U T S and it’s infeasible to show all outputs W H AT P R O B L E M S A R E G O O D F O R M A C H I N E L E A R N I N G ?

Slide 22

Slide 22 text

S L A C K H I G H L I G H T S M A N A G E T H E D E L U G E O F W O R K M E S S A G E S

Slide 23

Slide 23 text

M A K I N G D E C I S I O N S AT S C A L E for millions/billions of items or users W H AT P R O B L E M S A R E G O O D F O R M A C H I N E L E A R N I N G ?

Slide 24

Slide 24 text

ML MODEL OUTPUT PREDICTED LABELS CONFIDENCE % CAT CAT NOT NOT NOT SUPERVISED LEARNING CAT NOT CAT CAT NOT TRAINING SET UNSEEN DATA INPUT VALIDATION SET I M A G E S E A R C H “ C AT ”

Slide 25

Slide 25 text

D E C I S I O N S W I T H M A N Y I N P U T S D E C I S I O N S W I T H M A N Y O U T P U T S M A K I N G D E C I S I O N S AT S C A L E W H AT P R O B L E M S A R E G O O D F O R M A C H I N E L E A R N I N G ?

Slide 26

Slide 26 text

PREDICT DISCOVER OPTIMIZE DETECT RANK AUTOMATE stock prices housing prices sales health outcomes pricing user experience (personalization) recommendations bank fraud fake news fractures road hazards search results newsfeed recommendations patterns trends customer segmentation human tasks not easily delineated by rules W H AT P R O B L E M S A R E G O O D F O R M A C H I N E L E A R N I N G ?

Slide 27

Slide 27 text

U N S U P E R V I S E D L E A R N I N G D I S C O V E R PAT T E R N S

Slide 28

Slide 28 text

P R O B L E M How should I improve my fuel efficiency based on my driving behavior?

Slide 29

Slide 29 text

No content

Slide 30

Slide 30 text

8 clusters

Slide 31

Slide 31 text

What distinguishes those 8 clusters?

Slide 32

Slide 32 text

What are the biggest factors affecting fuel efficiency of our drivers? Aggression on highway Impatience on local roads Weather, terrain, traffic

Slide 33

Slide 33 text

NY Cabbie Grocery Go-Getter Highway Hustler Racecar Driver Suburban Scout Foxy Fighter Pilot Peaceful Sage Commuter

Slide 34

Slide 34 text

No content

Slide 35

Slide 35 text

A U T O M AT E C O M P L E X TA S K S D E E P L E A R N I N G

Slide 36

Slide 36 text

No content

Slide 37

Slide 37 text

S E L F - D R I V I N G C A R S

Slide 38

Slide 38 text

P R O B L E M A slice of the internet: How do we build products for such a diverse user base?

Slide 39

Slide 39 text

No content

Slide 40

Slide 40 text

No content

Slide 41

Slide 41 text

No content

Slide 42

Slide 42 text

No content

Slide 43

Slide 43 text

S O L U T I O N VISUAL SEARCH ENGINE FOR WEBSITES P R O B L E M How do we build products for such a diverse user base?

Slide 44

Slide 44 text

No content

Slide 45

Slide 45 text

Deep Learning: Under the hood (SIMPLIFIED) Convolutional variational auto-encoder Recreate the image Find similarities Learns how to interpret the structure of an image hidden layers DEEP

Slide 46

Slide 46 text

No content

Slide 47

Slide 47 text

No content

Slide 48

Slide 48 text

Slide 49

Slide 49 text

1. IDENTIFY THE RIGHT PROBLEMS TO USE ML TO SOLVE

Slide 50

Slide 50 text

2. FIND OUT: DO YOU HAVE THE DATA AND IS IT GOOD?

Slide 51

Slide 51 text

3. CONSIDER THE NON-ML ALTERNATIVE Is that good enough?

Slide 52

Slide 52 text

4. KNOW HOW INPUTS + OUTPUTS ARE RELATED

Slide 53

Slide 53 text

5. DESIGN FOR WHEN THE MODEL FAILS Because it will

Slide 54

Slide 54 text

USER TRUST Easy to lose Hard to win back

Slide 55

Slide 55 text

W H AT S H O U L D P R O D U C T P E O P L E B R I N G T O T H E TA B L E ? B A C KG R O U N D : W H AT I S M L? W H AT P R O B L E M S A R E G O O D F O R M L? W H Y N O W MACHINE LEARNING FROM A PRODUCT PERSPECTIVE B E YO N D T H E A L G O R I T H M : B U I L D I N G M L P R O D U C T S

Slide 56

Slide 56 text

PRIORITIZE BUILD LAUNCH LEARN MEASURE FOR SOFTWARE PRODUCTS P R O D U C T D E V E L O P M E N T C YC L E

Slide 57

Slide 57 text

CLASSIFY AS ML CONSIDER NON-ML GATHER & PREP DATA PRODUCT CHANGES? BUILD & EVALUATE MODELS THROW AWAY IDENTIFY MODEL WEAKNESSES COLLECT MORE DATA REBUILD & IMPROVE LAUNCH PRODUCTION MODEL ACCURACY % TRADEOFFS: ACCURACY VS COMPUTE POWER VS VISIBILITY FOR SOFTWARE PRODUCTS USING ML P R O D U C T D E V E L O P M E N T C YC L E PRIORITIZE BUILD LAUNCH LEARN MEASURE

Slide 58

Slide 58 text

INPUT OUTPUT MANY ML MODELS P R O D U C T S I N P R A C T I C E

Slide 59

Slide 59 text

B A C KG R O U N D : W H AT I S M L? B E YO N D T H E A L G O R I T H M : B U I L D I N G M L P R O D U C T S W H AT S H O U L D P R O D U C T P E O P L E B R I N G T O T H E TA B L E ? W H AT P R O B L E M S A R E G O O D F O R M L? W H Y N O W MACHINE LEARNING FROM A PRODUCT PERSPECTIVE L E A R N I N G F R O M D ATA W I T H O U T B E I N G E X P L I C I T LY P R O G R A M M E D M A N Y I N P U T S , M A N Y O U T P U T S M A K I N G D E C I S I O N S AT S C A L E D E S I G N F O R W H E N T H E M O D E L FA I L S L A U N C H , R E B U I L D & I M P R O V E . T R A D E O F F S

Slide 60

Slide 60 text

B E YO N D T H E A L G O R I T H M : B U I L D I N G M L P R O D U C T S W H AT YO U N E E D F O R M L B A C KG R O U N D : W H AT I S M L? W H AT P R O B L E M S A R E G O O D F O R M L? MACHINE LEARNING FROM A PRODUCT PERSPECTIVE W H Y N O W

Slide 61

Slide 61 text

MACHINE LEARNING PRODUCTS MATURING OF ML ALGORITHMS with open source tools and deep learning MASSIVE COMPUTE POWER Cloud computation GPU processing ACCESSIBILITY OF OPEN DATA CommonCrawl - petabytes ImageNet - 14M labeled C O N V E R G I N G T R E N D S … YOUR COMPETITORS ARE DOING IT NOT JUST FOR BIG COMPANIES EVEN INDIVIDUALS CAN DO IT

Slide 62

Slide 62 text

BUILD PRODUCTS THAT KNOW YOU BETTER THAN YOU KNOW YOURSELF CONSUMER M A C H I N E L E A R N I N G E N A B L E S …

Slide 63

Slide 63 text

YOUR DRIVING

Slide 64

Slide 64 text

“I wish my significant other understood me as well as Discover Weekly.” YOUR MUSIC TASTES

Slide 65

Slide 65 text

EVERYTHING YOU BUY

Slide 66

Slide 66 text

BUILD PRODUCTS THAT HELP BUSINESSES BE SUCCESSFUL SMB/ENTERPRISE M A C H I N E L E A R N I N G E N A B L E S …

Slide 67

Slide 67 text

YOUR WORKFLOW

Slide 68

Slide 68 text

EVERYTHING WE KNOW ABOUT SUCCESSFUL WEBSITES EVERYTHING WE KNOW ABOUT YOUR BUSINESS GOALS BUILD A SUCCESSFUL BUSINESS ONLINE

Slide 69

Slide 69 text

twitter: @ingachen THANK YOU!