Predictive Analytics World London| Oct 12, 2016 | Arif Wider & Christian Deger
Predictive Analytics for Vehicle Price Prediction
Delivered Continuously at AutoScout24

Dr. Arif Wider
Senior Consultant/Developer
awider@thoughtworks.com
@arifwider

Christian Deger
Chief Architect
cdeger@autoscout24.com
@cdeger

PL
S
RUS
UA
RO
CZ
D
NL
B
F
A
HR
I
E
BG
TR
18countries
2.4m+cars & motos
10m+users per
month

The task: A consumer-facing data product
5Predictive Analytics World London 2016 Predictive Analytics Delivered Continuously – A. Wider & C. Deger

The task: A consumer-facing data product
6Predictive Analytics World London 2016 Predictive Analytics Delivered Continuously – A. Wider & C. Deger

The task: A consumer-facing data product
7Predictive Analytics World London 2016 Predictive Analytics Delivered Continuously – A. Wider & C. Deger

The prediction model: Random forest
8
Volkswagen GolfCar listings of
last two years
Predictive Analytics World London 2016 Predictive Analytics Delivered Continuously – A. Wider & C. Deger

How to turn an R-based prediction model
into a high-performance web application?
9
?
Predictive Analytics World London 2016 Predictive Analytics Delivered Continuously – A. Wider & C. Deger

Traditional approach: Manually translate
model to an efficient implementation
10Predictive Analytics World London 2016 Predictive Analytics Delivered Continuously – A. Wider & C. Deger

Traditional approach: Manually translate
model to an efficient implementation again
11Predictive Analytics World London 2016 Predictive Analytics Delivered Continuously – A. Wider & C. Deger
:-/

Our approach: Automatically generate
implementation & deliver continuously
12
 Continuous Delivery!
Predictive Analytics World London 2016 Predictive Analytics Delivered Continuously – A. Wider & C. Deger

Application code in
one repository per
service.
CI
Deployment package
as artifact.
CD
Deliver package to
servers
Predictive Analytics World London 2016 Predictive Analytics Delivered Continuously – A. Wider & C. Deger
Typical continuous delivery pipeline

Continuous delivery pipelines
14
Prediction Model Pipeline
Web Application Pipeline
Predictive Analytics World London 2016 Predictive Analytics Delivered Continuously – A. Wider & C. Deger

The price for CD: Extensive model validation
15

Lessons learned
16
 Form cross-functional teams of
data scientists & software engineers!
 Set up usage reporting early to improve your
data product in a data-driven way.
 Generating gigabytes of Java code
is a challenge for the JVM
 Use the G1 garbage collector
 Do extensive warm-ups
Turn off Tiered Compilation
Predictive Analytics World London 2016 Predictive Analytics Delivered Continuously – A. Wider & C. Deger

Conclusions
17
 Continuous Delivery allows us to bring prediction
model changes live very quickly.
 Only extensive automated end-to-end tests provide
confidence to deploy to production automatically.
 Java code generation allows for very low response
times and excellent scalability for high loads but
requires plenty of memory.
Predictive Analytics World London 2016 Predictive Analytics Delivered Continuously – A. Wider & C. Deger

Thank you!
Questions?
– Arif Wider & Christian Deger –