SlideShare a Scribd company logo
1 of 18
Download to read offline
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 –

More Related Content

What's hot

SAP Run Live Truck - SAP Cloud Platform use cases
SAP Run Live Truck - SAP Cloud Platform use casesSAP Run Live Truck - SAP Cloud Platform use cases
SAP Run Live Truck - SAP Cloud Platform use casesTwan van den Broek
 
Independent Autodesk Building Performance Analysis Certificate_nickol_77 (1)
Independent Autodesk Building Performance Analysis Certificate_nickol_77 (1)Independent Autodesk Building Performance Analysis Certificate_nickol_77 (1)
Independent Autodesk Building Performance Analysis Certificate_nickol_77 (1)Nikol Todorova
 
Independent Autodesk Building Performance Analysis Certificate 2014_gamzeakcoru
Independent Autodesk Building Performance Analysis Certificate 2014_gamzeakcoruIndependent Autodesk Building Performance Analysis Certificate 2014_gamzeakcoru
Independent Autodesk Building Performance Analysis Certificate 2014_gamzeakcorugakcoru
 
Independent Autodesk Building Performance Analysis Certificate 2014_Alaaeldin
Independent Autodesk Building Performance Analysis Certificate 2014_AlaaeldinIndependent Autodesk Building Performance Analysis Certificate 2014_Alaaeldin
Independent Autodesk Building Performance Analysis Certificate 2014_AlaaeldinAlaaEldin AboElinin
 
Independent Autodesk Building Performance Analysis Certificate 2014_hiba.skh
Independent Autodesk Building Performance Analysis Certificate 2014_hiba.skhIndependent Autodesk Building Performance Analysis Certificate 2014_hiba.skh
Independent Autodesk Building Performance Analysis Certificate 2014_hiba.skhHeba Kharsah
 
SIGSPL.org | Labour, Arts and Analysis united
SIGSPL.org | Labour, Arts and Analysis unitedSIGSPL.org | Labour, Arts and Analysis united
SIGSPL.org | Labour, Arts and Analysis unitedSIGSPL.org
 
OSS Projects Knowledge Mining with CROSSMINER, OW2con'18, June 7-8, 2018
OSS Projects Knowledge Mining with CROSSMINER, OW2con'18, June 7-8, 2018OSS Projects Knowledge Mining with CROSSMINER, OW2con'18, June 7-8, 2018
OSS Projects Knowledge Mining with CROSSMINER, OW2con'18, June 7-8, 2018OW2
 
Independent Autodesk Building Performance Analysis Certificate 2014_artha125
Independent Autodesk Building Performance Analysis Certificate 2014_artha125Independent Autodesk Building Performance Analysis Certificate 2014_artha125
Independent Autodesk Building Performance Analysis Certificate 2014_artha125siddhartha reddy
 
Autodesk Building Performance Analysis Certificate 2016_alexvainshtein
Autodesk Building Performance Analysis Certificate 2016_alexvainshteinAutodesk Building Performance Analysis Certificate 2016_alexvainshtein
Autodesk Building Performance Analysis Certificate 2016_alexvainshteinAlex Vainshtein
 
Independent Autodesk Building Performance Analysis Certificate_Adil
Independent Autodesk Building Performance Analysis Certificate_AdilIndependent Autodesk Building Performance Analysis Certificate_Adil
Independent Autodesk Building Performance Analysis Certificate_AdilDr. Mohammad Adil
 

What's hot (11)

2013 05-27-yhat-about
2013 05-27-yhat-about2013 05-27-yhat-about
2013 05-27-yhat-about
 
SAP Run Live Truck - SAP Cloud Platform use cases
SAP Run Live Truck - SAP Cloud Platform use casesSAP Run Live Truck - SAP Cloud Platform use cases
SAP Run Live Truck - SAP Cloud Platform use cases
 
Independent Autodesk Building Performance Analysis Certificate_nickol_77 (1)
Independent Autodesk Building Performance Analysis Certificate_nickol_77 (1)Independent Autodesk Building Performance Analysis Certificate_nickol_77 (1)
Independent Autodesk Building Performance Analysis Certificate_nickol_77 (1)
 
Independent Autodesk Building Performance Analysis Certificate 2014_gamzeakcoru
Independent Autodesk Building Performance Analysis Certificate 2014_gamzeakcoruIndependent Autodesk Building Performance Analysis Certificate 2014_gamzeakcoru
Independent Autodesk Building Performance Analysis Certificate 2014_gamzeakcoru
 
Independent Autodesk Building Performance Analysis Certificate 2014_Alaaeldin
Independent Autodesk Building Performance Analysis Certificate 2014_AlaaeldinIndependent Autodesk Building Performance Analysis Certificate 2014_Alaaeldin
Independent Autodesk Building Performance Analysis Certificate 2014_Alaaeldin
 
Independent Autodesk Building Performance Analysis Certificate 2014_hiba.skh
Independent Autodesk Building Performance Analysis Certificate 2014_hiba.skhIndependent Autodesk Building Performance Analysis Certificate 2014_hiba.skh
Independent Autodesk Building Performance Analysis Certificate 2014_hiba.skh
 
SIGSPL.org | Labour, Arts and Analysis united
SIGSPL.org | Labour, Arts and Analysis unitedSIGSPL.org | Labour, Arts and Analysis united
SIGSPL.org | Labour, Arts and Analysis united
 
OSS Projects Knowledge Mining with CROSSMINER, OW2con'18, June 7-8, 2018
OSS Projects Knowledge Mining with CROSSMINER, OW2con'18, June 7-8, 2018OSS Projects Knowledge Mining with CROSSMINER, OW2con'18, June 7-8, 2018
OSS Projects Knowledge Mining with CROSSMINER, OW2con'18, June 7-8, 2018
 
Independent Autodesk Building Performance Analysis Certificate 2014_artha125
Independent Autodesk Building Performance Analysis Certificate 2014_artha125Independent Autodesk Building Performance Analysis Certificate 2014_artha125
Independent Autodesk Building Performance Analysis Certificate 2014_artha125
 
Autodesk Building Performance Analysis Certificate 2016_alexvainshtein
Autodesk Building Performance Analysis Certificate 2016_alexvainshteinAutodesk Building Performance Analysis Certificate 2016_alexvainshtein
Autodesk Building Performance Analysis Certificate 2016_alexvainshtein
 
Independent Autodesk Building Performance Analysis Certificate_Adil
Independent Autodesk Building Performance Analysis Certificate_AdilIndependent Autodesk Building Performance Analysis Certificate_Adil
Independent Autodesk Building Performance Analysis Certificate_Adil
 

Similar to Predictive Analytics for Vehicle Price Prediction - Delivered Continuously at AutoScout24

Towards Quality-Aware Development of Big Data Applications with DICE
Towards Quality-Aware Development of Big Data Applications with DICETowards Quality-Aware Development of Big Data Applications with DICE
Towards Quality-Aware Development of Big Data Applications with DICEPooyan Jamshidi
 
CIR Conferences - Cambridge Consultants
CIR Conferences - Cambridge ConsultantsCIR Conferences - Cambridge Consultants
CIR Conferences - Cambridge ConsultantsJustin Hayward
 
Building the Data-Driven Organization
Building the Data-Driven OrganizationBuilding the Data-Driven Organization
Building the Data-Driven OrganizationLora Cecere
 
Cadison world-issue-01-2013
Cadison world-issue-01-2013Cadison world-issue-01-2013
Cadison world-issue-01-2013CADISON
 
Inspir on presentation 15march2016
Inspir on presentation 15march2016Inspir on presentation 15march2016
Inspir on presentation 15march2016Bhaumik Dave
 
Dynniq & GoDataDriven - Shaping the future of traffic with IoT and AI
Dynniq & GoDataDriven - Shaping the future of traffic with IoT and AIDynniq & GoDataDriven - Shaping the future of traffic with IoT and AI
Dynniq & GoDataDriven - Shaping the future of traffic with IoT and AIBigDataExpo
 
SPLC 2019 Summit: Can Your Purchases Reverse Global Warming?
SPLC 2019 Summit: Can Your Purchases Reverse Global Warming?SPLC 2019 Summit: Can Your Purchases Reverse Global Warming?
SPLC 2019 Summit: Can Your Purchases Reverse Global Warming?SPLCouncil
 
DICE @ Innomatch 2015, 3rd Regional Innovation Fair, Arad, Romania
DICE @ Innomatch 2015, 3rd Regional Innovation Fair, Arad, RomaniaDICE @ Innomatch 2015, 3rd Regional Innovation Fair, Arad, Romania
DICE @ Innomatch 2015, 3rd Regional Innovation Fair, Arad, RomaniaInstitute e-Austria Timisoara
 
ChangeYourMind #2 - Internet of Things
ChangeYourMind #2 - Internet of ThingsChangeYourMind #2 - Internet of Things
ChangeYourMind #2 - Internet of ThingsChangeGroup
 
It’s Not About What You Know. It’s About What You Can Do
It’s Not About What You Know. It’s About What You Can DoIt’s Not About What You Know. It’s About What You Can Do
It’s Not About What You Know. It’s About What You Can DoMichal Hodinka
 
CADISON world Issue-1-2013
CADISON world Issue-1-2013CADISON world Issue-1-2013
CADISON world Issue-1-2013CADISON
 
Cloud Native Cost Optimization UCC
Cloud Native Cost Optimization UCCCloud Native Cost Optimization UCC
Cloud Native Cost Optimization UCCAdrian Cockcroft
 
Driving Innovation with Kanban at Jaguar Land Rover
Driving Innovation with Kanban at Jaguar Land RoverDriving Innovation with Kanban at Jaguar Land Rover
Driving Innovation with Kanban at Jaguar Land RoverLeanKit
 
PwC accelerator why how Mateusz Nowak
PwC accelerator why how Mateusz NowakPwC accelerator why how Mateusz Nowak
PwC accelerator why how Mateusz NowakPaweł Przybyszewski
 
Achieving Software Assurance with Hybrid Analysis Mapping
Achieving Software Assurance with Hybrid Analysis Mapping  Achieving Software Assurance with Hybrid Analysis Mapping
Achieving Software Assurance with Hybrid Analysis Mapping Denim Group
 
The business case for SD WAN in the enterprise
The business case for SD WAN in the enterprise The business case for SD WAN in the enterprise
The business case for SD WAN in the enterprise Colt Technology Services
 
Cloud Expo 2015: DICE: Developing Data-Intensive Cloud Applications with Iter...
Cloud Expo 2015: DICE: Developing Data-Intensive Cloud Applications with Iter...Cloud Expo 2015: DICE: Developing Data-Intensive Cloud Applications with Iter...
Cloud Expo 2015: DICE: Developing Data-Intensive Cloud Applications with Iter...DICE-H2020
 
[WSO2Con USA 2018] APIs and Microservices
[WSO2Con USA 2018] APIs and Microservices[WSO2Con USA 2018] APIs and Microservices
[WSO2Con USA 2018] APIs and MicroservicesWSO2
 
Optimizing Your Supply Chain with Neo4j
Optimizing Your Supply Chain with Neo4jOptimizing Your Supply Chain with Neo4j
Optimizing Your Supply Chain with Neo4jNeo4j
 

Similar to Predictive Analytics for Vehicle Price Prediction - Delivered Continuously at AutoScout24 (20)

Towards Quality-Aware Development of Big Data Applications with DICE
Towards Quality-Aware Development of Big Data Applications with DICETowards Quality-Aware Development of Big Data Applications with DICE
Towards Quality-Aware Development of Big Data Applications with DICE
 
CIR Conferences - Cambridge Consultants
CIR Conferences - Cambridge ConsultantsCIR Conferences - Cambridge Consultants
CIR Conferences - Cambridge Consultants
 
Building the Data-Driven Organization
Building the Data-Driven OrganizationBuilding the Data-Driven Organization
Building the Data-Driven Organization
 
Cadison world-issue-01-2013
Cadison world-issue-01-2013Cadison world-issue-01-2013
Cadison world-issue-01-2013
 
Inspir on presentation 15march2016
Inspir on presentation 15march2016Inspir on presentation 15march2016
Inspir on presentation 15march2016
 
Dynniq & GoDataDriven - Shaping the future of traffic with IoT and AI
Dynniq & GoDataDriven - Shaping the future of traffic with IoT and AIDynniq & GoDataDriven - Shaping the future of traffic with IoT and AI
Dynniq & GoDataDriven - Shaping the future of traffic with IoT and AI
 
SPLC 2019 Summit: Can Your Purchases Reverse Global Warming?
SPLC 2019 Summit: Can Your Purchases Reverse Global Warming?SPLC 2019 Summit: Can Your Purchases Reverse Global Warming?
SPLC 2019 Summit: Can Your Purchases Reverse Global Warming?
 
DICE @ Innomatch 2015, 3rd Regional Innovation Fair, Arad, Romania
DICE @ Innomatch 2015, 3rd Regional Innovation Fair, Arad, RomaniaDICE @ Innomatch 2015, 3rd Regional Innovation Fair, Arad, Romania
DICE @ Innomatch 2015, 3rd Regional Innovation Fair, Arad, Romania
 
ChangeYourMind #2 - Internet of Things
ChangeYourMind #2 - Internet of ThingsChangeYourMind #2 - Internet of Things
ChangeYourMind #2 - Internet of Things
 
It’s Not About What You Know. It’s About What You Can Do
It’s Not About What You Know. It’s About What You Can DoIt’s Not About What You Know. It’s About What You Can Do
It’s Not About What You Know. It’s About What You Can Do
 
Meetup Spark UDF performance
Meetup Spark UDF performanceMeetup Spark UDF performance
Meetup Spark UDF performance
 
CADISON world Issue-1-2013
CADISON world Issue-1-2013CADISON world Issue-1-2013
CADISON world Issue-1-2013
 
Cloud Native Cost Optimization UCC
Cloud Native Cost Optimization UCCCloud Native Cost Optimization UCC
Cloud Native Cost Optimization UCC
 
Driving Innovation with Kanban at Jaguar Land Rover
Driving Innovation with Kanban at Jaguar Land RoverDriving Innovation with Kanban at Jaguar Land Rover
Driving Innovation with Kanban at Jaguar Land Rover
 
PwC accelerator why how Mateusz Nowak
PwC accelerator why how Mateusz NowakPwC accelerator why how Mateusz Nowak
PwC accelerator why how Mateusz Nowak
 
Achieving Software Assurance with Hybrid Analysis Mapping
Achieving Software Assurance with Hybrid Analysis Mapping  Achieving Software Assurance with Hybrid Analysis Mapping
Achieving Software Assurance with Hybrid Analysis Mapping
 
The business case for SD WAN in the enterprise
The business case for SD WAN in the enterprise The business case for SD WAN in the enterprise
The business case for SD WAN in the enterprise
 
Cloud Expo 2015: DICE: Developing Data-Intensive Cloud Applications with Iter...
Cloud Expo 2015: DICE: Developing Data-Intensive Cloud Applications with Iter...Cloud Expo 2015: DICE: Developing Data-Intensive Cloud Applications with Iter...
Cloud Expo 2015: DICE: Developing Data-Intensive Cloud Applications with Iter...
 
[WSO2Con USA 2018] APIs and Microservices
[WSO2Con USA 2018] APIs and Microservices[WSO2Con USA 2018] APIs and Microservices
[WSO2Con USA 2018] APIs and Microservices
 
Optimizing Your Supply Chain with Neo4j
Optimizing Your Supply Chain with Neo4jOptimizing Your Supply Chain with Neo4j
Optimizing Your Supply Chain with Neo4j
 

More from Dr. Arif Wider

Data Mesh - It's not about technology, it's about people
Data Mesh - It's not about technology, it's about peopleData Mesh - It's not about technology, it's about people
Data Mesh - It's not about technology, it's about peopleDr. Arif Wider
 
Data Mesh in Practice - How Europe's Leading Online Platform for Fashion Goes...
Data Mesh in Practice - How Europe's Leading Online Platform for Fashion Goes...Data Mesh in Practice - How Europe's Leading Online Platform for Fashion Goes...
Data Mesh in Practice - How Europe's Leading Online Platform for Fashion Goes...Dr. Arif Wider
 
Continuous Intelligence: Keeping your AI Application in Production
Continuous Intelligence: Keeping your AI Application in ProductionContinuous Intelligence: Keeping your AI Application in Production
Continuous Intelligence: Keeping your AI Application in ProductionDr. Arif Wider
 
Continuous Intelligence: Keeping Your AI Application in Production (NDC Sydne...
Continuous Intelligence: Keeping Your AI Application in Production (NDC Sydne...Continuous Intelligence: Keeping Your AI Application in Production (NDC Sydne...
Continuous Intelligence: Keeping Your AI Application in Production (NDC Sydne...Dr. Arif Wider
 
Continuous Intelligence: Moving Machine Learning into Production Reliably
Continuous Intelligence: Moving Machine Learning into Production ReliablyContinuous Intelligence: Moving Machine Learning into Production Reliably
Continuous Intelligence: Moving Machine Learning into Production ReliablyDr. Arif Wider
 
Continuous Intelligence: Keeping your AI Application in Production
Continuous Intelligence: Keeping your AI Application in ProductionContinuous Intelligence: Keeping your AI Application in Production
Continuous Intelligence: Keeping your AI Application in ProductionDr. Arif Wider
 
DataDevOps: A Manifesto for a DevOps-like Culture Shift in Data & Analytics
DataDevOps: A Manifesto for a DevOps-like Culture Shift in Data & AnalyticsDataDevOps: A Manifesto for a DevOps-like Culture Shift in Data & Analytics
DataDevOps: A Manifesto for a DevOps-like Culture Shift in Data & AnalyticsDr. Arif Wider
 
DataDevOps: A Manifesto for a DevOps-like Culture Shift in Data & Analytics
DataDevOps: A Manifesto for a DevOps-like Culture Shift in Data & AnalyticsDataDevOps: A Manifesto for a DevOps-like Culture Shift in Data & Analytics
DataDevOps: A Manifesto for a DevOps-like Culture Shift in Data & AnalyticsDr. Arif Wider
 
DataDevOps - A Manifesto on Shared Data Responsibility in Times of Microservices
DataDevOps - A Manifesto on Shared Data Responsibility in Times of MicroservicesDataDevOps - A Manifesto on Shared Data Responsibility in Times of Microservices
DataDevOps - A Manifesto on Shared Data Responsibility in Times of MicroservicesDr. Arif Wider
 
A High-Performance Solution to Microservice UI Composition @ XConf Hamburg
A High-Performance Solution to Microservice UI Composition @ XConf HamburgA High-Performance Solution to Microservice UI Composition @ XConf Hamburg
A High-Performance Solution to Microservice UI Composition @ XConf HamburgDr. Arif Wider
 
An Unexpected Solution to Microservices UI Composition
An Unexpected Solution to Microservices UI CompositionAn Unexpected Solution to Microservices UI Composition
An Unexpected Solution to Microservices UI CompositionDr. Arif Wider
 

More from Dr. Arif Wider (11)

Data Mesh - It's not about technology, it's about people
Data Mesh - It's not about technology, it's about peopleData Mesh - It's not about technology, it's about people
Data Mesh - It's not about technology, it's about people
 
Data Mesh in Practice - How Europe's Leading Online Platform for Fashion Goes...
Data Mesh in Practice - How Europe's Leading Online Platform for Fashion Goes...Data Mesh in Practice - How Europe's Leading Online Platform for Fashion Goes...
Data Mesh in Practice - How Europe's Leading Online Platform for Fashion Goes...
 
Continuous Intelligence: Keeping your AI Application in Production
Continuous Intelligence: Keeping your AI Application in ProductionContinuous Intelligence: Keeping your AI Application in Production
Continuous Intelligence: Keeping your AI Application in Production
 
Continuous Intelligence: Keeping Your AI Application in Production (NDC Sydne...
Continuous Intelligence: Keeping Your AI Application in Production (NDC Sydne...Continuous Intelligence: Keeping Your AI Application in Production (NDC Sydne...
Continuous Intelligence: Keeping Your AI Application in Production (NDC Sydne...
 
Continuous Intelligence: Moving Machine Learning into Production Reliably
Continuous Intelligence: Moving Machine Learning into Production ReliablyContinuous Intelligence: Moving Machine Learning into Production Reliably
Continuous Intelligence: Moving Machine Learning into Production Reliably
 
Continuous Intelligence: Keeping your AI Application in Production
Continuous Intelligence: Keeping your AI Application in ProductionContinuous Intelligence: Keeping your AI Application in Production
Continuous Intelligence: Keeping your AI Application in Production
 
DataDevOps: A Manifesto for a DevOps-like Culture Shift in Data & Analytics
DataDevOps: A Manifesto for a DevOps-like Culture Shift in Data & AnalyticsDataDevOps: A Manifesto for a DevOps-like Culture Shift in Data & Analytics
DataDevOps: A Manifesto for a DevOps-like Culture Shift in Data & Analytics
 
DataDevOps: A Manifesto for a DevOps-like Culture Shift in Data & Analytics
DataDevOps: A Manifesto for a DevOps-like Culture Shift in Data & AnalyticsDataDevOps: A Manifesto for a DevOps-like Culture Shift in Data & Analytics
DataDevOps: A Manifesto for a DevOps-like Culture Shift in Data & Analytics
 
DataDevOps - A Manifesto on Shared Data Responsibility in Times of Microservices
DataDevOps - A Manifesto on Shared Data Responsibility in Times of MicroservicesDataDevOps - A Manifesto on Shared Data Responsibility in Times of Microservices
DataDevOps - A Manifesto on Shared Data Responsibility in Times of Microservices
 
A High-Performance Solution to Microservice UI Composition @ XConf Hamburg
A High-Performance Solution to Microservice UI Composition @ XConf HamburgA High-Performance Solution to Microservice UI Composition @ XConf Hamburg
A High-Performance Solution to Microservice UI Composition @ XConf Hamburg
 
An Unexpected Solution to Microservices UI Composition
An Unexpected Solution to Microservices UI CompositionAn Unexpected Solution to Microservices UI Composition
An Unexpected Solution to Microservices UI Composition
 

Recently uploaded

Bank Loan Approval Analysis: A Comprehensive Data Analysis Project
Bank Loan Approval Analysis: A Comprehensive Data Analysis ProjectBank Loan Approval Analysis: A Comprehensive Data Analysis Project
Bank Loan Approval Analysis: A Comprehensive Data Analysis ProjectBoston Institute of Analytics
 
Digital Marketing Plan, how digital marketing works
Digital Marketing Plan, how digital marketing worksDigital Marketing Plan, how digital marketing works
Digital Marketing Plan, how digital marketing worksdeepakthakur548787
 
Semantic Shed - Squashing and Squeezing.pptx
Semantic Shed - Squashing and Squeezing.pptxSemantic Shed - Squashing and Squeezing.pptx
Semantic Shed - Squashing and Squeezing.pptxMike Bennett
 
专业一比一美国俄亥俄大学毕业证成绩单pdf电子版制作修改
专业一比一美国俄亥俄大学毕业证成绩单pdf电子版制作修改专业一比一美国俄亥俄大学毕业证成绩单pdf电子版制作修改
专业一比一美国俄亥俄大学毕业证成绩单pdf电子版制作修改yuu sss
 
The Power of Data-Driven Storytelling_ Unveiling the Layers of Insight.pptx
The Power of Data-Driven Storytelling_ Unveiling the Layers of Insight.pptxThe Power of Data-Driven Storytelling_ Unveiling the Layers of Insight.pptx
The Power of Data-Driven Storytelling_ Unveiling the Layers of Insight.pptxTasha Penwell
 
Student Profile Sample report on improving academic performance by uniting gr...
Student Profile Sample report on improving academic performance by uniting gr...Student Profile Sample report on improving academic performance by uniting gr...
Student Profile Sample report on improving academic performance by uniting gr...Seán Kennedy
 
Advanced Machine Learning for Business Professionals
Advanced Machine Learning for Business ProfessionalsAdvanced Machine Learning for Business Professionals
Advanced Machine Learning for Business ProfessionalsVICTOR MAESTRE RAMIREZ
 
Generative AI for Social Good at Open Data Science East 2024
Generative AI for Social Good at Open Data Science East 2024Generative AI for Social Good at Open Data Science East 2024
Generative AI for Social Good at Open Data Science East 2024Colleen Farrelly
 
Easter Eggs From Star Wars and in cars 1 and 2
Easter Eggs From Star Wars and in cars 1 and 2Easter Eggs From Star Wars and in cars 1 and 2
Easter Eggs From Star Wars and in cars 1 and 217djon017
 
English-8-Q4-W3-Synthesizing-Essential-Information-From-Various-Sources-1.pdf
English-8-Q4-W3-Synthesizing-Essential-Information-From-Various-Sources-1.pdfEnglish-8-Q4-W3-Synthesizing-Essential-Information-From-Various-Sources-1.pdf
English-8-Q4-W3-Synthesizing-Essential-Information-From-Various-Sources-1.pdfblazblazml
 
Conf42-LLM_Adding Generative AI to Real-Time Streaming Pipelines
Conf42-LLM_Adding Generative AI to Real-Time Streaming PipelinesConf42-LLM_Adding Generative AI to Real-Time Streaming Pipelines
Conf42-LLM_Adding Generative AI to Real-Time Streaming PipelinesTimothy Spann
 
Data Factory in Microsoft Fabric (MsBIP #82)
Data Factory in Microsoft Fabric (MsBIP #82)Data Factory in Microsoft Fabric (MsBIP #82)
Data Factory in Microsoft Fabric (MsBIP #82)Cathrine Wilhelmsen
 
Data Analysis Project : Targeting the Right Customers, Presentation on Bank M...
Data Analysis Project : Targeting the Right Customers, Presentation on Bank M...Data Analysis Project : Targeting the Right Customers, Presentation on Bank M...
Data Analysis Project : Targeting the Right Customers, Presentation on Bank M...Boston Institute of Analytics
 
FAIR, FAIRsharing, FAIR Cookbook and ELIXIR - Sansone SA - Boston 2024
FAIR, FAIRsharing, FAIR Cookbook and ELIXIR - Sansone SA - Boston 2024FAIR, FAIRsharing, FAIR Cookbook and ELIXIR - Sansone SA - Boston 2024
FAIR, FAIRsharing, FAIR Cookbook and ELIXIR - Sansone SA - Boston 2024Susanna-Assunta Sansone
 
INTRODUCTION TO Natural language processing
INTRODUCTION TO Natural language processingINTRODUCTION TO Natural language processing
INTRODUCTION TO Natural language processingsocarem879
 
Cyber awareness ppt on the recorded data
Cyber awareness ppt on the recorded dataCyber awareness ppt on the recorded data
Cyber awareness ppt on the recorded dataTecnoIncentive
 
Data Analysis Project Presentation: Unveiling Your Ideal Customer, Bank Custo...
Data Analysis Project Presentation: Unveiling Your Ideal Customer, Bank Custo...Data Analysis Project Presentation: Unveiling Your Ideal Customer, Bank Custo...
Data Analysis Project Presentation: Unveiling Your Ideal Customer, Bank Custo...Boston Institute of Analytics
 
办美国阿肯色大学小石城分校毕业证成绩单pdf电子版制作修改#真实留信入库#永久存档#真实可查#diploma#degree
办美国阿肯色大学小石城分校毕业证成绩单pdf电子版制作修改#真实留信入库#永久存档#真实可查#diploma#degree办美国阿肯色大学小石城分校毕业证成绩单pdf电子版制作修改#真实留信入库#永久存档#真实可查#diploma#degree
办美国阿肯色大学小石城分校毕业证成绩单pdf电子版制作修改#真实留信入库#永久存档#真实可查#diploma#degreeyuu sss
 
modul pembelajaran robotic Workshop _ by Slidesgo.pptx
modul pembelajaran robotic Workshop _ by Slidesgo.pptxmodul pembelajaran robotic Workshop _ by Slidesgo.pptx
modul pembelajaran robotic Workshop _ by Slidesgo.pptxaleedritatuxx
 
NLP Data Science Project Presentation:Predicting Heart Disease with NLP Data ...
NLP Data Science Project Presentation:Predicting Heart Disease with NLP Data ...NLP Data Science Project Presentation:Predicting Heart Disease with NLP Data ...
NLP Data Science Project Presentation:Predicting Heart Disease with NLP Data ...Boston Institute of Analytics
 

Recently uploaded (20)

Bank Loan Approval Analysis: A Comprehensive Data Analysis Project
Bank Loan Approval Analysis: A Comprehensive Data Analysis ProjectBank Loan Approval Analysis: A Comprehensive Data Analysis Project
Bank Loan Approval Analysis: A Comprehensive Data Analysis Project
 
Digital Marketing Plan, how digital marketing works
Digital Marketing Plan, how digital marketing worksDigital Marketing Plan, how digital marketing works
Digital Marketing Plan, how digital marketing works
 
Semantic Shed - Squashing and Squeezing.pptx
Semantic Shed - Squashing and Squeezing.pptxSemantic Shed - Squashing and Squeezing.pptx
Semantic Shed - Squashing and Squeezing.pptx
 
专业一比一美国俄亥俄大学毕业证成绩单pdf电子版制作修改
专业一比一美国俄亥俄大学毕业证成绩单pdf电子版制作修改专业一比一美国俄亥俄大学毕业证成绩单pdf电子版制作修改
专业一比一美国俄亥俄大学毕业证成绩单pdf电子版制作修改
 
The Power of Data-Driven Storytelling_ Unveiling the Layers of Insight.pptx
The Power of Data-Driven Storytelling_ Unveiling the Layers of Insight.pptxThe Power of Data-Driven Storytelling_ Unveiling the Layers of Insight.pptx
The Power of Data-Driven Storytelling_ Unveiling the Layers of Insight.pptx
 
Student Profile Sample report on improving academic performance by uniting gr...
Student Profile Sample report on improving academic performance by uniting gr...Student Profile Sample report on improving academic performance by uniting gr...
Student Profile Sample report on improving academic performance by uniting gr...
 
Advanced Machine Learning for Business Professionals
Advanced Machine Learning for Business ProfessionalsAdvanced Machine Learning for Business Professionals
Advanced Machine Learning for Business Professionals
 
Generative AI for Social Good at Open Data Science East 2024
Generative AI for Social Good at Open Data Science East 2024Generative AI for Social Good at Open Data Science East 2024
Generative AI for Social Good at Open Data Science East 2024
 
Easter Eggs From Star Wars and in cars 1 and 2
Easter Eggs From Star Wars and in cars 1 and 2Easter Eggs From Star Wars and in cars 1 and 2
Easter Eggs From Star Wars and in cars 1 and 2
 
English-8-Q4-W3-Synthesizing-Essential-Information-From-Various-Sources-1.pdf
English-8-Q4-W3-Synthesizing-Essential-Information-From-Various-Sources-1.pdfEnglish-8-Q4-W3-Synthesizing-Essential-Information-From-Various-Sources-1.pdf
English-8-Q4-W3-Synthesizing-Essential-Information-From-Various-Sources-1.pdf
 
Conf42-LLM_Adding Generative AI to Real-Time Streaming Pipelines
Conf42-LLM_Adding Generative AI to Real-Time Streaming PipelinesConf42-LLM_Adding Generative AI to Real-Time Streaming Pipelines
Conf42-LLM_Adding Generative AI to Real-Time Streaming Pipelines
 
Data Factory in Microsoft Fabric (MsBIP #82)
Data Factory in Microsoft Fabric (MsBIP #82)Data Factory in Microsoft Fabric (MsBIP #82)
Data Factory in Microsoft Fabric (MsBIP #82)
 
Data Analysis Project : Targeting the Right Customers, Presentation on Bank M...
Data Analysis Project : Targeting the Right Customers, Presentation on Bank M...Data Analysis Project : Targeting the Right Customers, Presentation on Bank M...
Data Analysis Project : Targeting the Right Customers, Presentation on Bank M...
 
FAIR, FAIRsharing, FAIR Cookbook and ELIXIR - Sansone SA - Boston 2024
FAIR, FAIRsharing, FAIR Cookbook and ELIXIR - Sansone SA - Boston 2024FAIR, FAIRsharing, FAIR Cookbook and ELIXIR - Sansone SA - Boston 2024
FAIR, FAIRsharing, FAIR Cookbook and ELIXIR - Sansone SA - Boston 2024
 
INTRODUCTION TO Natural language processing
INTRODUCTION TO Natural language processingINTRODUCTION TO Natural language processing
INTRODUCTION TO Natural language processing
 
Cyber awareness ppt on the recorded data
Cyber awareness ppt on the recorded dataCyber awareness ppt on the recorded data
Cyber awareness ppt on the recorded data
 
Data Analysis Project Presentation: Unveiling Your Ideal Customer, Bank Custo...
Data Analysis Project Presentation: Unveiling Your Ideal Customer, Bank Custo...Data Analysis Project Presentation: Unveiling Your Ideal Customer, Bank Custo...
Data Analysis Project Presentation: Unveiling Your Ideal Customer, Bank Custo...
 
办美国阿肯色大学小石城分校毕业证成绩单pdf电子版制作修改#真实留信入库#永久存档#真实可查#diploma#degree
办美国阿肯色大学小石城分校毕业证成绩单pdf电子版制作修改#真实留信入库#永久存档#真实可查#diploma#degree办美国阿肯色大学小石城分校毕业证成绩单pdf电子版制作修改#真实留信入库#永久存档#真实可查#diploma#degree
办美国阿肯色大学小石城分校毕业证成绩单pdf电子版制作修改#真实留信入库#永久存档#真实可查#diploma#degree
 
modul pembelajaran robotic Workshop _ by Slidesgo.pptx
modul pembelajaran robotic Workshop _ by Slidesgo.pptxmodul pembelajaran robotic Workshop _ by Slidesgo.pptx
modul pembelajaran robotic Workshop _ by Slidesgo.pptx
 
NLP Data Science Project Presentation:Predicting Heart Disease with NLP Data ...
NLP Data Science Project Presentation:Predicting Heart Disease with NLP Data ...NLP Data Science Project Presentation:Predicting Heart Disease with NLP Data ...
NLP Data Science Project Presentation:Predicting Heart Disease with NLP Data ...
 

Predictive Analytics for Vehicle Price Prediction - Delivered Continuously at AutoScout24

  • 1. Predictive Analytics World London| Oct 12, 2016 | Arif Wider & Christian Deger Predictive Analytics for Vehicle Price Prediction Delivered Continuously at AutoScout24
  • 2. Dr. Arif Wider Senior Consultant/Developer awider@thoughtworks.com @arifwider
  • 5. The task: A consumer-facing data product 5Predictive Analytics World London 2016 Predictive Analytics Delivered Continuously – A. Wider & C. Deger
  • 6. The task: A consumer-facing data product 6Predictive Analytics World London 2016 Predictive Analytics Delivered Continuously – A. Wider & C. Deger
  • 7. The task: A consumer-facing data product 7Predictive Analytics World London 2016 Predictive Analytics Delivered Continuously – A. Wider & C. Deger
  • 8. 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
  • 9. 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
  • 10. Traditional approach: Manually translate model to an efficient implementation 10Predictive Analytics World London 2016 Predictive Analytics Delivered Continuously – A. Wider & C. Deger
  • 11. Traditional approach: Manually translate model to an efficient implementation again 11Predictive Analytics World London 2016 Predictive Analytics Delivered Continuously – A. Wider & C. Deger :-/
  • 12. Our approach: Automatically generate implementation & deliver continuously 12  Continuous Delivery! Predictive Analytics World London 2016 Predictive Analytics Delivered Continuously – A. Wider & C. Deger
  • 13. 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
  • 14. Continuous delivery pipelines 14 Prediction Model Pipeline Web Application Pipeline Predictive Analytics World London 2016 Predictive Analytics Delivered Continuously – A. Wider & C. Deger
  • 15. The price for CD: Extensive model validation 15
  • 16. 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
  • 17. 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
  • 18. Thank you! Questions? – Arif Wider & Christian Deger –