Page 1
© Prof. dr. Philippe Baecke
PROF DR. PHILIPPE BAECKE
Professor of Business Analytics and Big Data� Prof. at Vlerick Business School� Affiliated Prof. at Ghent University� Visiting Prof. at Trinity College (Dublin)� Visiting Prof. at UCD & Kaplan Business School (Hong Kong)� Visiting Prof. at Université de Namur
Research� Business Analytics & Big Data� (electronic) Customer Relationship Management� Digital Marketing� Spatial & network analysis
Ghent Campus, Office [email protected] .: +3292109228
https://be.linkedin.com/in/philippebaecke
Page 2
THE VALUE OF ANALYTICS IN FINANCIAL SERVICES
PROF. DR. PHILIPPE BAECKE
Page 3
© Prof. dr. Philippe Baecke
DigitalFinancial Services
Impact
Page 4
© Prof. dr. Philippe Baecke
IMPACT FROM DIGITAL
Margins
8%
12%
18%
23% 22%
44%
0%
10%
20%
30%
40%
50%
<100000 EUR 100000 -
200000 EUR
200000 -
300000 EUR
300000 -
500000 EUR
500000 -
750000 EUR
>750000 EUR
Consolidation of agents and brokers
2014
2016
(source: Benthurst & co – 2016)
Page 5
© Prof. dr. Philippe Baecke
IMPACT FROM DIGITAL
Cost reduction
Customer experience
Page 6
© Prof. dr. Philippe Baecke
BIG DATA
Page 7
© Prof. dr. Philippe Baecke
BIG DATA
Google trends: Big Data
PhDEssays on Data Augmentation:
The Value of Additional Information Creating Business Value with Big Data
Data Driven Marketing
Page 8
© Prof. dr. Philippe Baecke
BIG DATA STRATEGY
Page 9
© Prof. dr. Philippe Baecke
DATA COLLECTION
Trans-actions
E-mail
www
Social
sensors
Mobile
callDepartment 1
Department 2
Department 3
Company
Customer
sales
…
Touch points Business
Data silo
Data silo
Data silo
Data silo
Data silo
Page 10
© Prof. dr. Philippe Baecke
DATA COLLECTION
Trans-actions
E-mail
www
Social
sensors
Mobile
callDepartment 1
Department 2
Department 3
Company
Customer
sales
…
Touch points Business
Single customer view
Page 11
© Prof. dr. Philippe Baecke
ANALYSE - DESCRIPTIVE
Data collection / IT infrastructure
Descriptive Analytics
Data collection / IT infrastructure
Page 12
© Prof. dr. Philippe Baecke
DISCOVERING
Descriptive
Predictive
Page 13
© Prof. dr. Philippe Baecke
ANALYSE - PREDICTIVE
Data collection / IT infrastructure
Descriptive Analytics
Data collection / IT infrastructure
PredictiveAnalytics
Page 14
© Prof. dr. Philippe Baecke
ANALYSE - PREDICTIVE
Available data Predictions
(unknown)
T
Today
Descriptive Analytics
Today T-1Independent
variables
T-1
TodayDependent
Variable
(known)
Descriptive Analytics
Data mining
technique
Crash
Page 15
© Prof. dr. Philippe Baecke
ANALYSE - PREDICTIVE
Probability ?
ChurnCrash
Fraud
Purchase
…
Default
Page 16
© Prof. dr. Philippe Baecke
BIG DATA
Page 17
© Prof. dr. Philippe Baecke
BIG DATA
Descriptive Analytics
Data collection / IT infrastructure
PredictiveAnalytics
Web/clickstream
Social
Mobilesensors
…
Text
Big Data
Page 18
© Prof. dr. Philippe Baecke
BIG DATA - TELEMATICS
Claims
Baecke P. & Bocca L. (2017) - The value of vehicle telematics data in insurance risk selection processes
� Claim history (bonus malus, years without claim, …)
� Customer specific (age, driving experience, …)
� Car specific (kilowatt, brand, …)
Predictive performance
Random
Perfect
+
Driving behaviour
+50%
Page 19
© Prof. dr. Philippe Baecke
BIG DATA - TELEMATICS
Descriptive driver feedback
Page 20
© Prof. dr. Philippe Baecke
BIG DATA - SOCIAL
Tobback E. & Martens D. - Credit scoring for microfinance using Facebook data
Network of Friends Pseudo-Network of Friends
vs
A B
DC
Page 21
© Prof. dr. Philippe Baecke
BIG DATA - SOCIAL
Tobback E. & Martens D. - Credit scoring for microfinance using Facebook data
29 traditional variables
Predictive performance
Random
Perfect
Default
+� Friends� Likes� Comments� …
Page 22
© Prof. dr. Philippe Baecke
BIG DATA - SOCIAL
Tobback E. & Martens D. - Credit scoring for microfinance using Facebook data
29 traditional variables
Predictive performance
Random
Perfect
+50%Default
+� Friends� Likes� Comments� …
Page 23
© Prof. dr. Philippe Baecke
PRESCRIPTIVE ANALYTICS
Descriptive Analytics
PredictiveAnalytics
PrescriptiveAnalytics
Data collection / IT infrastructure
Page 24
© Prof. dr. Philippe Baecke
PRESCRIPTIVE ANALYTICS
Human input replaced by business rules or optimisation algorithms
Page 25
© Prof. dr. Philippe Baecke
ROBO-ADVISER
Risk assessment(based on 8 questions)
� Automatic portfolio suggestion (mainly ETFs)� Automatic dividend reinvestments� Automatic tax loss harvesting� Convenient dashboard� …
Page 26
© Prof. dr. Philippe Baecke
ARTIFICIAL INTELLIGENCE
Descriptive Analytics
Data collection / IT infrastructure
PredictiveAnalytics
Big Data
Web/clickstream
Social
Mobilesensors
…
Text
PrescriptiveAnalytics
Artificial intelligence
Page 27
© Prof. dr. Philippe Baecke
ARTIFICIAL INTELLIGENCE
1997Chess
Kasparov vs
IBM Deepblue
2011JeopadryKen, Brad
vs IBM Watson
Page 28
© Prof. dr. Philippe Baecke
COGNITIVE COMPUTINGDescriptive Analytics
PredictiveAnalytics
2007�2011: Jeopardy – Human vs machine
Page 29
© Prof. dr. Philippe Baecke
COGNITIVE COMPUTINGDescriptive Analytics
PredictiveAnalytics
Human
Create corpus
Q&A training
Page 30
© Prof. dr. Philippe Baecke
COGNITIVE COMPUTINGDescriptive Analytics
PredictiveAnalytics
US Cities
Page 31
© Prof. dr. Philippe Baecke
COGNITIVE COMPUTINGDescriptive Analytics
PredictiveAnalytics
Not perfect yet …
Page 32
© Prof. dr. Philippe Baecke
CUSTOMER CAREDescriptive Analytics
PredictiveAnalytics
Phase 1:
Phase 2:
Page 33
© Prof. dr. Philippe Baecke
ARTIFICIAL INTELLIGENCE
1997Chess
Kasparov vs
IBM Deepblue
2011JeopadryKen, Brad
vs IBM Watson
2016Go
Lee Sedolvs
Google Alpha Go
Page 34
© Prof. dr. Philippe Baecke
DEEP LEARNING
+ able to detect very complex patterns
- Needs a lot of data observations to be trained well
100 billion neurons
Neuron
Axon
Page 35
© Prof. dr. Philippe Baecke
DEEP LEARNING
0 – no damage
0.25 – light damage
0.5 – moderate damage
0.75 – heavy damage
1 – total destruction
Karoon Rashedi Nia (2017) - Automatic Building Damage Assessment Using Deep Learning and Ground-Level Image Data
Page 36
© Prof. dr. Philippe Baecke
DEEP LEARNING
Facial analytics to predict life expectancy
Page 37
© Prof. dr. Philippe Baecke
DEEP LEARNING
Page 38
© Prof. dr. Philippe Baecke
BIG DATA
Page 39
© Prof. dr. Philippe Baecke
Algorithms Algorithms
Page 40
© Prof. dr. Philippe Baecke
ADOPTION BARRIERS � ENABLERS
CultureCulturePeoplePeople
Customer, privacy
Customer, privacy
Tools, systems,processes
Tools, systems,processes
Page 41
© Prof. dr. Philippe Baecke
CUSTOMER & PRIVACY
Page 42
Prof. dr. Philippe BaeckeAssociate Professor of Marketing
be.linkedin.com/in/philippebaecke
[email protected]
Thank you
Vlerick Business SchoolReep 19000 Gent, Belgiumwww.vlerick.com
Programme director:� Creating Business Value with Big Data� Strategic Data Driven Marketing
Interest to collaborate?