Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
Scaling_Machine_Learning_at_Holiday_Extras_-_MUC.pdf
Search
Rebecca Vickery
November 07, 2019
0
1.2k
Scaling_Machine_Learning_at_Holiday_Extras_-_MUC.pdf
Rebecca Vickery
November 07, 2019
Tweet
Share
More Decks by Rebecca Vickery
See All by Rebecca Vickery
Pair Programming with AI
rebeccavickery
1
67
Machine Learning for Everyone
rebeccavickery
0
17
Data Preparation and the Importance of How Machines Learn
rebeccavickery
0
140
Scaling Machine Learning at Holiday Extras (Big Data LDN 2019))
rebeccavickery
0
120
Gender Bias, Why we Need More Women in Tech
rebeccavickery
0
1.2k
The Fastest Way to Learn Data Science
rebeccavickery
0
48
Employing Google Cloud Machine Learning Engine to Develop Models in Production
rebeccavickery
0
1.2k
Featured
See All Featured
Building an army of robots
kneath
300
41k
Fashionably flexible responsive web design (full day workshop)
malarkey
397
65k
Scaling GitHub
holman
457
140k
Java REST API Framework Comparison - PWX 2021
mraible
PRO
18
6.9k
Responsive Adventures: Dirty Tricks From The Dark Corners of Front-End
smashingmag
243
20k
Fontdeck: Realign not Redesign
paulrobertlloyd
75
4.9k
Building Better People: How to give real-time feedback that sticks.
wjessup
353
18k
The World Runs on Bad Software
bkeepers
PRO
61
6.7k
Learning to Love Humans: Emotional Interface Design
aarron
266
39k
How GitHub (no longer) Works
holman
304
140k
Code Reviewing Like a Champion
maltzj
513
39k
The Illustrated Children's Guide to Kubernetes
chrisshort
28
46k
Transcript
Scaling Machine Learning at Holiday Extras REBECCA VICKERY | DATA
SCIENTIST @vickdata
Travel planning is time consuming Airport parking Airport hotels Airport
lounges Travel insurance Holiday money Port products Car hire Airport transfers 582 minutes Over 46 days* Travel Planning *Facebook commissioned consumer research company GfK
Optimising consumer decision making Airport parking Airport hotels Airport lounges
Travel insurance Holiday money Port products Car hire Airport transfers Less Hassle. More Holiday Trip recommendations
The machine learning process Historic Data (Input) (Input Algorithm Learns
Mapping Predictions (Output)
Automated bidding Ad targeting Channel optimisation 1 Ad spend 2
Commercial 3 Customer Experience 4 Marketing Lots of other processes to optimise Automated pricing Allocation Revenue optimisation Automated call handling Personalised experiences Intelligent messaging Optimising send frequency
Machine learning needs to scale
Deploying machine learning is hard Scaling is even harder
Tools - Data Scientists Open source Lack Software Development expertise
Mainly Python c Flaticon
Tools - Software Engineers Different tools Lack ML/Data expertise Mainly
Javascript c Flaticon
Data science process The wrong kind of independence c Flaticon
People Small data science team Science + software experts are
rare c Flaticon
Two types of deployment
Bespoke Solutions “Ideas are worth nothing unless executed”, Derek Sivers
c Daniel Moyo
Unused Models Many models never make it to production “Ideas
are worth nothing unless executed”, Derek Sivers
Time to model deployment Model development = days to weeks
Model deployment = weeks to never! “Ideas are worth nothing unless executed”, Derek Sivers
The Google Way
c Flaticon __init__.py task.py setup.py model.py Model Package
Repeatable, Reusable Process __init__.py task.py setup.py model.py Model Package
None
Not Quite!
Collaborative Project
ML Proxy (bespoke ML microservice)
Monitoring - Model Performance
Monitoring - AI Platform Performance
AI Platform A technical solution but also a strategic solution
c Google
The right kind of independence c flaticon Data Scientists can
use preferred tools
The right kind of independence c flaticon Repeatable process for
deployment of most models
Faster time to production c flaticon Fully Managed service
Faster time to production c flaticon Fast response from Google
Cloud Support
Extensibility c flaticon.com Multiple models and versions
Customisable c flaticon.com Regularly release support for newer versions of
tools
Time to model deployment Model development = days to weeks
Model deployment = hours to days “Ideas are worth nothing unless executed”, Derek Sivers
Less Hassle. More Holiday Trip recommendations
Thank you @vickdata