Real time analysis of vehicle data
to diagnose and predict failure
Complexity of
vehicles is growing
exponentially
Existing
diagnostic tools
cannot keep up
Issue Impact
Cyber security vulnerabilities Recall ~1.4 Million Cars
Software incompatibility between Electric
Vehicle control unit and battery control
module may cause propulsion system to
shut down
Recall ~5,600 Electric Cars
Software flaw may cause the hybrid
system to shut down while driving
Recall ~1.9 Million Hybrid Cars
Flaw in the continuously variable
automatic transmission software may
subject the drive pulley shaft to high stress
Recall 143,000 Cars in the U.S.
RECALLS
Source: Various news outlets and manufacturer s websites, McKinsey & Company
SOLUTION
A platform that uses machine learning and statistical analysis to detect anomalies and
predict failures in real time for automotive vehicles
Manufacturing
Advanced analytics that detect problems
in vehicles before they get on the road
Fleet Managers
Real-time monitoring of the vehicles on the road
to reduce warranties and maintenance costs
SOLUTION
Growing
complexity
More sensors and
electronics
Connected vehicles
Advanced and
autonomous software
features
DTC
(Diagnostic Trouble Codes) that
set off the Check Engine Light
Trouble codes are
becoming less
informative and less
reliable
More data
More vehicle data is
being collected, both
during manufacturing
and on the road, than
ever before
WHY NOW
*source:	IHS;	Autofacts;	Frost	&	Sullivan;	KPMG;	HBR;	Bain;	McKinsey;	NHTSA;	Technavio;	NaBonal	Automobile	Dealers	AssociaBon;	OEM	reports;	Capgemini;	
Thomson	Reuters;	Gartner;	Oxford	Economics;	Strategy&	analysis	
THE GLOBAL
AUTOMOTIVE MARKET $150B
90M
New cars
produced per year
=	
$1,665
Software supplier revenue
per car manufactured
Vehicle sales
$2.45 Trillion
Insurance, financing, aftermarket
$1.7 Trillion
Supplier
$0.85 Trillion
Software
$150 Billion
Hardware
$700 Billion
Collaboration
Structured POC to
demonstrate diagnostics and
prognostics capability.
POC
(Proof of Concept)
Develop a prototype to
integrate the analytics and
monitor select vehicles.
PILOT EXPAND
(SaaS)
Expand prototype into a full
deployment by increasing the
number of monitored vehicles.
Validation Integration Deployment
BUSINESS MODEL
Geared for automotive systems
(focused and validated with vehicle components)
Works with any vehicle model
(not exclusive to single manufacturer or product)
Scales with vehicle complexity
(support thousands of signals from growing
number of sensors and components)
Support any OBDII hardware & data
(analysis adapts to data from a variety of data
collection hardware)
Rich data
(more than your typical OBDII data)
Leverage manufacturing data
(data from newly manufactured vehicles
and their malfunctions)
Manufacturers Telematics General AI
COMPETITION
Greta Cutulenco, CEO
§ Software Engineer, University of Waterloo
§ 2 years of research experience in embedded and real
time systems as part of her master s
§ 3 years of experience working with software systems in
automotive, aerospace, and nuclear fields
§ She has worked at Magna, AECL, and Qualcomm
Sebastian Fischmeister, Chief Scientist
§  PhD, PEng, Computer Science
§  Associate Professor, University of Waterloo
§  Associate Director of WatCAR
§  Over 16 years of research experience
§  Extensive experience managing a team of over 15
people and working with million dollar budgets
Jean-Christophe Petkovich, CTO
§  Master of Computer Science and PhD candidate in
Computer Engineering, University of Waterloo
§  5 years of research experience in the fields of
statistics and machine learning
§  Significant contributions in the open sourced
software community
§  He has worked at QNX and Bombardier
Gonen Hollander, COO
§  MBA, Rotman School of Management, University
of Toronto
§  7 years of navy service, as Missile Ship Tactical
Officer and Basic Training Team Leader
§  Over 6 years of management and leadership
development
§  Experience with operations, business strategy
and business development
Prashant Raghav, Chief Data Officer
§  Master of Computer Science, University of Waterloo
§  He has worked at Amazon, SAS, and Lenovo
§  Extensive experience in scaling analysis for BigData
§  Over 4 years experience with distributed systems
including Hadoop and Spark
Himesh Patel, Marketing & Business Dev.
§  Management Engineer, University of Waterloo
§  Experience in managing product development
and optimizing internal company processes
§  He has worked with Whitehat Security,
Broadcom, and D2L
TEAM
Mike Donoughe
§  25 years VP at Chrysler overseeing
manufacturing and engineering
§  EVP at Tesla Motors overseeing vehicle
engineering, manufacturing, quality,
and supply chain
§  C-Level executive with extensive
experience leading companies in all
phases of execution
Chris Kondogiani
§  15 years of leadership experience with
Fortune organizations, startups, and
new ventures
§  Over 10 years experience with vehicle
engineering at Chrysler
§  MBA with Finance and Marketing focus
ADVISORS
founders@acerta.ca

Acerta Deck

  • 1.
    Real time analysisof vehicle data to diagnose and predict failure
  • 2.
    Complexity of vehicles isgrowing exponentially Existing diagnostic tools cannot keep up
  • 3.
    Issue Impact Cyber securityvulnerabilities Recall ~1.4 Million Cars Software incompatibility between Electric Vehicle control unit and battery control module may cause propulsion system to shut down Recall ~5,600 Electric Cars Software flaw may cause the hybrid system to shut down while driving Recall ~1.9 Million Hybrid Cars Flaw in the continuously variable automatic transmission software may subject the drive pulley shaft to high stress Recall 143,000 Cars in the U.S. RECALLS Source: Various news outlets and manufacturer s websites, McKinsey & Company
  • 4.
    SOLUTION A platform thatuses machine learning and statistical analysis to detect anomalies and predict failures in real time for automotive vehicles
  • 5.
    Manufacturing Advanced analytics thatdetect problems in vehicles before they get on the road Fleet Managers Real-time monitoring of the vehicles on the road to reduce warranties and maintenance costs SOLUTION
  • 6.
    Growing complexity More sensors and electronics Connectedvehicles Advanced and autonomous software features DTC (Diagnostic Trouble Codes) that set off the Check Engine Light Trouble codes are becoming less informative and less reliable More data More vehicle data is being collected, both during manufacturing and on the road, than ever before WHY NOW
  • 7.
    *source: IHS; Autofacts; Frost & Sullivan; KPMG; HBR; Bain; McKinsey; NHTSA; Technavio; NaBonal Automobile Dealers AssociaBon; OEM reports; Capgemini; Thomson Reuters; Gartner; Oxford Economics; Strategy& analysis THE GLOBAL AUTOMOTIVE MARKET$150B 90M New cars produced per year = $1,665 Software supplier revenue per car manufactured Vehicle sales $2.45 Trillion Insurance, financing, aftermarket $1.7 Trillion Supplier $0.85 Trillion Software $150 Billion Hardware $700 Billion
  • 8.
    Collaboration Structured POC to demonstratediagnostics and prognostics capability. POC (Proof of Concept) Develop a prototype to integrate the analytics and monitor select vehicles. PILOT EXPAND (SaaS) Expand prototype into a full deployment by increasing the number of monitored vehicles. Validation Integration Deployment BUSINESS MODEL
  • 9.
    Geared for automotivesystems (focused and validated with vehicle components) Works with any vehicle model (not exclusive to single manufacturer or product) Scales with vehicle complexity (support thousands of signals from growing number of sensors and components) Support any OBDII hardware & data (analysis adapts to data from a variety of data collection hardware) Rich data (more than your typical OBDII data) Leverage manufacturing data (data from newly manufactured vehicles and their malfunctions) Manufacturers Telematics General AI COMPETITION
  • 10.
    Greta Cutulenco, CEO § SoftwareEngineer, University of Waterloo § 2 years of research experience in embedded and real time systems as part of her master s § 3 years of experience working with software systems in automotive, aerospace, and nuclear fields § She has worked at Magna, AECL, and Qualcomm Sebastian Fischmeister, Chief Scientist §  PhD, PEng, Computer Science §  Associate Professor, University of Waterloo §  Associate Director of WatCAR §  Over 16 years of research experience §  Extensive experience managing a team of over 15 people and working with million dollar budgets Jean-Christophe Petkovich, CTO §  Master of Computer Science and PhD candidate in Computer Engineering, University of Waterloo §  5 years of research experience in the fields of statistics and machine learning §  Significant contributions in the open sourced software community §  He has worked at QNX and Bombardier Gonen Hollander, COO §  MBA, Rotman School of Management, University of Toronto §  7 years of navy service, as Missile Ship Tactical Officer and Basic Training Team Leader §  Over 6 years of management and leadership development §  Experience with operations, business strategy and business development Prashant Raghav, Chief Data Officer §  Master of Computer Science, University of Waterloo §  He has worked at Amazon, SAS, and Lenovo §  Extensive experience in scaling analysis for BigData §  Over 4 years experience with distributed systems including Hadoop and Spark Himesh Patel, Marketing & Business Dev. §  Management Engineer, University of Waterloo §  Experience in managing product development and optimizing internal company processes §  He has worked with Whitehat Security, Broadcom, and D2L TEAM
  • 11.
    Mike Donoughe §  25years VP at Chrysler overseeing manufacturing and engineering §  EVP at Tesla Motors overseeing vehicle engineering, manufacturing, quality, and supply chain §  C-Level executive with extensive experience leading companies in all phases of execution Chris Kondogiani §  15 years of leadership experience with Fortune organizations, startups, and new ventures §  Over 10 years experience with vehicle engineering at Chrysler §  MBA with Finance and Marketing focus ADVISORS
  • 12.