SlideShare a Scribd company logo
1 of 24
The Data Science behind Predictive
Maintenance in Connected Vehicles
Esther Vasiete
Srivatsan Ramanujam
Pivotal Data Science
Data Engineers Guild -
Meetup
June-21, 2016
Picture credit (from L to R):
http://www.techlicious.com/blog/ericsson-mobility-report-internet-connected-devices/
http://www.mdpi.com/1424-8220/14/10/19260/htm
http://www.thehindubusinessline.com/info-tech/other-gadgets/care-for-a-connected-car/article5777444.ece
Devices are Increasingly Connected
How can these connected devices in our home be smart enough to make daily
life easier?
How does thisā€¦
ā€¦become this?
By recognizing this
And by processing this
Sensors + Other Unstructured Data
How can we know a tree has
fallen on a power line before
the residents complain?
How can we use data
to help prevent
accidents like the Macondo Disaster ?
Gene Sequencing
Smart Grids
COST TO SEQUENCE
ONE GENOME
HAS FALLEN FROM
$100M IN 2001
TO $10K IN 2011
TO $1K IN 2014
READING SMART METERS
EVERY 15 MINUTES IS
3000X MORE
DATA INTENSIVE
Stock Market
Social Media
FACEBOOK UPLOADS
250 MILLION
PHOTOS EACH DAY
In all industries billions of data points represent
opportunities for the Internet of Things
Oil Exploration
Video Surveillance
OIL RIGS GENERATE
25000
DATA POINTS
PER SECOND
Medical Imaging
Mobile Sensors
To realize this opportunity requires the right tools and
techniques
Problem
Formulation
Modeling Step
Data StepApps Step
Data Lake
Ingest
Business Levers
Dashboard/App
PL/X
Modelingā€¢ Data cleaning
ā€¢ Data Exploration
ā€¢ Feature
Engineering
Model Validation
Feedback loop for
continuous
model improvement
Driver and
Vehicle Meta
Data
Data Ingestion
Platform
āœ”
āœ” āœ” āœ” āœ”āœ” āœ” āœ”
Data to Apps
Data Science
Use-cases for connected cars
1
Data Science Use-Cases
1
ā— Predictive Car Maintenance
ā€’ More accurately predict part failure
ā€’ Optimize part repair and replacement schedule
ā— Leveraging Driving Behaviour
ā€’ Useful to differentiate insurance pricing based on driving
style
ā€’ Optimize car design
ā— Improving GPS Systems
ā€’ Establish baseline for traffic congestion
ā€’ Create more meaningful metrics for routing
ā€’ Infer public transportation effects on traffic
ā€’ Predict how long incidents would take to clear
ā— Predictive Power for Assistance
Systems
ā€’ Optimize fuel efficiency
ā€’ Predict the future state of a car in the next 2
minutes (starts, stops, emergency braking)
ā— Traffic Light Assistance
ā€’ Signal timing of traffic lights
ā€’ Crowd sourcing of traffic signals
ā€’ Optimize traffic light patterns to reduce congestion
Preventive Maintenance for
Connected Vehicles
1
On-Board Diagnostics
Diagnostic Trouble Codes (DTC)
Unscheduled repairs
AB1029 ā€“ Power steering pump replacement
CT3408 ā€“ Wheel alignment
Solving the preventive maintenance problem
Automakers
Customer
Satisfaction
Auto Repairs
Data Sources for Predictive Maintenance
VIN
Timestamp
DTC Code
Odometer
Speed
Acceleration
Engine Temperature
Engine Torque GPS
Coordinates
etc.
VIN
Date vehicle in
Date vehicle out
Repair code
Parts replaced
Warranty claims
Repair Comments
Vehicle Data Car Repairs Data
Predicting Job Type from Diagnostic Trouble Codes
(DTCs)
Time
Job Type:
Transmission
Job Type:
Transmission
Engine
Job Type:
Regular check
DTC: B DTC:
B,
P, C
DTC: U
DTC: B DTC: B
DTC:
B, P, C, U
DTC:
P, B, U
DTC: P DTC: B DTC:
B,P
DTC:
B,P
Can the DTCs
observed here predict
this Job Type?
Can the DTCs observed
here predict this Job
Type?
Can the DTCs observed
here predict this Job
Type?
Predicting Job Type: a multi-class classification
problem
DF
12
10
DF
12
15
DF
29
80
AB
10
29
AB
16
22
AB
16
25
AB
86
22
CT
34
02
CT
34
08
CT
35
60
CT
24
09
Vehicle
Features
Hierarchical Classification Framework
Vehicle
Features
DF
12
10
DF
12
15
DF
29
80
AB
10
29
AB
16
22
AB
16
25
AB
86
22
CT
34
02
CT
34
08
CT
35
60
CT
24
09
Model Parallelism
One or more job on the same day
Multi-labeling problem
One-vs-rest classifiers
built in parallel
1
0
0
1
0 1
0
Class 1
Class 2
Class 3
One-vs-Rest Classification
Red vs.
Non Red
On Segment 1
Green vs.
Non Green
On Segment 2
Blue vs.
Non Blue
On Segment N
ā€¢ Predictive maintenance problems are challenging because
DTC signals are not always symptomatic of an ensuing
repair.
ā€¢ Given the hierarchical nature of repair codes, we built a two
stage hierarchical classification framework comprising a top-
down cascade of classifiers.
ā€¢ Major system jobs can be predicted earlier to the repair
date.
Key Takeaways
Reference Architecture
%%publish
model info.
/
Microservices
(Spring Boot)
/load_model
/score_model
Spring Cloud Data Flow
vehicle data (streaming)
connector
exploratory data
analysis & model
training
Rabbit/Kafka
source
training (offline)
scoring (online)
/
web or mobile app dashboard
Data Science for Connected Vehicles

More Related Content

What's hot

Smart traffic management system
Smart traffic management systemSmart traffic management system
Smart traffic management system
Chirag Dalal
Ā 
Smart parking system
Smart parking systemSmart parking system
Smart parking system
slmnsvn
Ā 

What's hot (15)

Smart traffic management system
Smart traffic management systemSmart traffic management system
Smart traffic management system
Ā 
Automotive Cybersecurity Challenges for Automated Vehicles: Jonathan Petit
Automotive Cybersecurity Challenges for Automated Vehicles: Jonathan PetitAutomotive Cybersecurity Challenges for Automated Vehicles: Jonathan Petit
Automotive Cybersecurity Challenges for Automated Vehicles: Jonathan Petit
Ā 
Smart traffic managment system real time (stmsrt)
Smart traffic managment system real time (stmsrt)Smart traffic managment system real time (stmsrt)
Smart traffic managment system real time (stmsrt)
Ā 
Intelligent Traffic monitoring System
Intelligent Traffic monitoring SystemIntelligent Traffic monitoring System
Intelligent Traffic monitoring System
Ā 
All Aboard With Sendyne
All Aboard With SendyneAll Aboard With Sendyne
All Aboard With Sendyne
Ā 
Smart parking
Smart parkingSmart parking
Smart parking
Ā 
SmartParking: A Secure and Intelligent Parking System Using NOTICE
SmartParking: A Secure and Intelligent Parking System Using NOTICESmartParking: A Secure and Intelligent Parking System Using NOTICE
SmartParking: A Secure and Intelligent Parking System Using NOTICE
Ā 
Smart parking system
Smart parking systemSmart parking system
Smart parking system
Ā 
Smart parking
Smart parkingSmart parking
Smart parking
Ā 
Google driver less car presentation (ppt) 2017 Hemant pratap singh
Google driver less car presentation (ppt) 2017 Hemant pratap singh Google driver less car presentation (ppt) 2017 Hemant pratap singh
Google driver less car presentation (ppt) 2017 Hemant pratap singh
Ā 
Smart car parking system
Smart car parking systemSmart car parking system
Smart car parking system
Ā 
Intelligent transportion system
Intelligent transportion systemIntelligent transportion system
Intelligent transportion system
Ā 
Smart parking
Smart parkingSmart parking
Smart parking
Ā 
ITS and its history
ITS and its historyITS and its history
ITS and its history
Ā 
Advanced Driver Assistance System using FPGA
Advanced Driver Assistance System using FPGAAdvanced Driver Assistance System using FPGA
Advanced Driver Assistance System using FPGA
Ā 

Similar to Data Science for Connected Vehicles

Data management for OCMS and infra-electrical depots
Data management for OCMS and infra-electrical depotsData management for OCMS and infra-electrical depots
Data management for OCMS and infra-electrical depots
Sifiso. Lukhele
Ā 

Similar to Data Science for Connected Vehicles (20)

IRJET- IoT based Smart BLACK BOX System
IRJET- IoT based Smart BLACK BOX SystemIRJET- IoT based Smart BLACK BOX System
IRJET- IoT based Smart BLACK BOX System
Ā 
SMART E-TOLL SYSTEM
SMART E-TOLL SYSTEMSMART E-TOLL SYSTEM
SMART E-TOLL SYSTEM
Ā 
IoT based E-vehicle monitoring system using sensors and imaging processing a...
IoT based E-vehicle monitoring system using sensors and  imaging processing a...IoT based E-vehicle monitoring system using sensors and  imaging processing a...
IoT based E-vehicle monitoring system using sensors and imaging processing a...
Ā 
Smart Fleet Management with IoT
Smart Fleet Management with IoTSmart Fleet Management with IoT
Smart Fleet Management with IoT
Ā 
IRJET- Smart Card Based Automated Toll Plaza System
IRJET-  	  Smart Card Based Automated Toll Plaza SystemIRJET-  	  Smart Card Based Automated Toll Plaza System
IRJET- Smart Card Based Automated Toll Plaza System
Ā 
G041024547
G041024547G041024547
G041024547
Ā 
IRJET- A Methodology: Iot Based Drowsy Driving Warning and Traffic Collis...
IRJET-  	  A Methodology: Iot Based Drowsy Driving Warning and Traffic Collis...IRJET-  	  A Methodology: Iot Based Drowsy Driving Warning and Traffic Collis...
IRJET- A Methodology: Iot Based Drowsy Driving Warning and Traffic Collis...
Ā 
IRJET- Intelligent Traffic Management System
IRJET- Intelligent Traffic Management SystemIRJET- Intelligent Traffic Management System
IRJET- Intelligent Traffic Management System
Ā 
Autonomous Vehicles: Technologies, Economics, and Opportunities
Autonomous Vehicles: Technologies, Economics, and OpportunitiesAutonomous Vehicles: Technologies, Economics, and Opportunities
Autonomous Vehicles: Technologies, Economics, and Opportunities
Ā 
SMART SOLUTION FOR RESOLVING HEAVY TRAFFIC USING IOT
SMART SOLUTION FOR RESOLVING HEAVY TRAFFIC USING IOTSMART SOLUTION FOR RESOLVING HEAVY TRAFFIC USING IOT
SMART SOLUTION FOR RESOLVING HEAVY TRAFFIC USING IOT
Ā 
IRJET- Smart Vehicle with Crash Detection and Emergency Vehicle Dispatch with...
IRJET- Smart Vehicle with Crash Detection and Emergency Vehicle Dispatch with...IRJET- Smart Vehicle with Crash Detection and Emergency Vehicle Dispatch with...
IRJET- Smart Vehicle with Crash Detection and Emergency Vehicle Dispatch with...
Ā 
CAV Smart Work Zones
CAV Smart Work ZonesCAV Smart Work Zones
CAV Smart Work Zones
Ā 
A survey paper on Optimal Solution on Vehicular Adhoc Network for Congestion ...
A survey paper on Optimal Solution on Vehicular Adhoc Network for Congestion ...A survey paper on Optimal Solution on Vehicular Adhoc Network for Congestion ...
A survey paper on Optimal Solution on Vehicular Adhoc Network for Congestion ...
Ā 
Design and Implementation of Car Black box for Evidence Collection System to ...
Design and Implementation of Car Black box for Evidence Collection System to ...Design and Implementation of Car Black box for Evidence Collection System to ...
Design and Implementation of Car Black box for Evidence Collection System to ...
Ā 
IRJET- Traffic Sign Recognition for Autonomous Cars
IRJET- Traffic Sign Recognition for Autonomous CarsIRJET- Traffic Sign Recognition for Autonomous Cars
IRJET- Traffic Sign Recognition for Autonomous Cars
Ā 
IRJET- Computerized Vehicle Number Plate Recognition and Fine Generation
IRJET-  	  Computerized Vehicle Number Plate Recognition and Fine GenerationIRJET-  	  Computerized Vehicle Number Plate Recognition and Fine Generation
IRJET- Computerized Vehicle Number Plate Recognition and Fine Generation
Ā 
IRJET - Electronic Turnpike Automation System with Penalty Analyzer
IRJET - Electronic Turnpike Automation System with Penalty AnalyzerIRJET - Electronic Turnpike Automation System with Penalty Analyzer
IRJET - Electronic Turnpike Automation System with Penalty Analyzer
Ā 
IRJET- Congestion Reducing System through Sensors, Image Processors and Vanet...
IRJET- Congestion Reducing System through Sensors, Image Processors and Vanet...IRJET- Congestion Reducing System through Sensors, Image Processors and Vanet...
IRJET- Congestion Reducing System through Sensors, Image Processors and Vanet...
Ā 
VEHICLE TO VEHICLE COMMUNICATION FOR ACCIDENT-AVOIDANCE SYSTEM
VEHICLE TO VEHICLE COMMUNICATION FOR ACCIDENT-AVOIDANCE SYSTEMVEHICLE TO VEHICLE COMMUNICATION FOR ACCIDENT-AVOIDANCE SYSTEM
VEHICLE TO VEHICLE COMMUNICATION FOR ACCIDENT-AVOIDANCE SYSTEM
Ā 
Data management for OCMS and infra-electrical depots
Data management for OCMS and infra-electrical depotsData management for OCMS and infra-electrical depots
Data management for OCMS and infra-electrical depots
Ā 

Recently uploaded

Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Safe Software
Ā 

Recently uploaded (20)

šŸ¬ The future of MySQL is Postgres šŸ˜
šŸ¬  The future of MySQL is Postgres   šŸ˜šŸ¬  The future of MySQL is Postgres   šŸ˜
šŸ¬ The future of MySQL is Postgres šŸ˜
Ā 
AWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of TerraformAWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of Terraform
Ā 
A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)
Ā 
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law DevelopmentsTrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
Ā 
Strategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a FresherStrategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a Fresher
Ā 
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024
Ā 
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Ā 
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdfUnderstanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
Ā 
Automating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps ScriptAutomating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps Script
Ā 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected Worker
Ā 
2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...
Ā 
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationFrom Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
Ā 
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemkeProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
Ā 
TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data DiscoveryTrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
Ā 
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Ā 
Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...
Ā 
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Ā 
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
Ā 
Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdf
Ā 
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Ā 

Data Science for Connected Vehicles

  • 1. The Data Science behind Predictive Maintenance in Connected Vehicles Esther Vasiete Srivatsan Ramanujam Pivotal Data Science Data Engineers Guild - Meetup June-21, 2016
  • 2. Picture credit (from L to R): http://www.techlicious.com/blog/ericsson-mobility-report-internet-connected-devices/ http://www.mdpi.com/1424-8220/14/10/19260/htm http://www.thehindubusinessline.com/info-tech/other-gadgets/care-for-a-connected-car/article5777444.ece Devices are Increasingly Connected
  • 3.
  • 4. How can these connected devices in our home be smart enough to make daily life easier?
  • 5. How does thisā€¦ ā€¦become this? By recognizing this And by processing this Sensors + Other Unstructured Data
  • 6. How can we know a tree has fallen on a power line before the residents complain?
  • 7. How can we use data to help prevent accidents like the Macondo Disaster ?
  • 8. Gene Sequencing Smart Grids COST TO SEQUENCE ONE GENOME HAS FALLEN FROM $100M IN 2001 TO $10K IN 2011 TO $1K IN 2014 READING SMART METERS EVERY 15 MINUTES IS 3000X MORE DATA INTENSIVE Stock Market Social Media FACEBOOK UPLOADS 250 MILLION PHOTOS EACH DAY In all industries billions of data points represent opportunities for the Internet of Things Oil Exploration Video Surveillance OIL RIGS GENERATE 25000 DATA POINTS PER SECOND Medical Imaging Mobile Sensors
  • 9. To realize this opportunity requires the right tools and techniques Problem Formulation Modeling Step Data StepApps Step
  • 10.
  • 11. Data Lake Ingest Business Levers Dashboard/App PL/X Modelingā€¢ Data cleaning ā€¢ Data Exploration ā€¢ Feature Engineering Model Validation Feedback loop for continuous model improvement Driver and Vehicle Meta Data Data Ingestion Platform āœ” āœ” āœ” āœ” āœ”āœ” āœ” āœ” Data to Apps
  • 12. Data Science Use-cases for connected cars 1
  • 13. Data Science Use-Cases 1 ā— Predictive Car Maintenance ā€’ More accurately predict part failure ā€’ Optimize part repair and replacement schedule ā— Leveraging Driving Behaviour ā€’ Useful to differentiate insurance pricing based on driving style ā€’ Optimize car design ā— Improving GPS Systems ā€’ Establish baseline for traffic congestion ā€’ Create more meaningful metrics for routing ā€’ Infer public transportation effects on traffic ā€’ Predict how long incidents would take to clear ā— Predictive Power for Assistance Systems ā€’ Optimize fuel efficiency ā€’ Predict the future state of a car in the next 2 minutes (starts, stops, emergency braking) ā— Traffic Light Assistance ā€’ Signal timing of traffic lights ā€’ Crowd sourcing of traffic signals ā€’ Optimize traffic light patterns to reduce congestion
  • 15. On-Board Diagnostics Diagnostic Trouble Codes (DTC) Unscheduled repairs AB1029 ā€“ Power steering pump replacement CT3408 ā€“ Wheel alignment
  • 16. Solving the preventive maintenance problem Automakers Customer Satisfaction Auto Repairs
  • 17. Data Sources for Predictive Maintenance VIN Timestamp DTC Code Odometer Speed Acceleration Engine Temperature Engine Torque GPS Coordinates etc. VIN Date vehicle in Date vehicle out Repair code Parts replaced Warranty claims Repair Comments Vehicle Data Car Repairs Data
  • 18. Predicting Job Type from Diagnostic Trouble Codes (DTCs) Time Job Type: Transmission Job Type: Transmission Engine Job Type: Regular check DTC: B DTC: B, P, C DTC: U DTC: B DTC: B DTC: B, P, C, U DTC: P, B, U DTC: P DTC: B DTC: B,P DTC: B,P Can the DTCs observed here predict this Job Type? Can the DTCs observed here predict this Job Type? Can the DTCs observed here predict this Job Type?
  • 19. Predicting Job Type: a multi-class classification problem DF 12 10 DF 12 15 DF 29 80 AB 10 29 AB 16 22 AB 16 25 AB 86 22 CT 34 02 CT 34 08 CT 35 60 CT 24 09 Vehicle Features
  • 21. Model Parallelism One or more job on the same day Multi-labeling problem One-vs-rest classifiers built in parallel 1 0 0 1 0 1 0 Class 1 Class 2 Class 3 One-vs-Rest Classification Red vs. Non Red On Segment 1 Green vs. Non Green On Segment 2 Blue vs. Non Blue On Segment N
  • 22. ā€¢ Predictive maintenance problems are challenging because DTC signals are not always symptomatic of an ensuing repair. ā€¢ Given the hierarchical nature of repair codes, we built a two stage hierarchical classification framework comprising a top- down cascade of classifiers. ā€¢ Major system jobs can be predicted earlier to the repair date. Key Takeaways
  • 23. Reference Architecture %%publish model info. / Microservices (Spring Boot) /load_model /score_model Spring Cloud Data Flow vehicle data (streaming) connector exploratory data analysis & model training Rabbit/Kafka source training (offline) scoring (online) / web or mobile app dashboard