SlideShare a Scribd company logo
Berengueres	

Opportunities in Etihad
miles program
Review of findings UAEU study on loyalty program data
February 2013
EB2013.02.28
CONFIDENTIAL AND PROPRIETARY
Any use of this material without specific permission of Jose Berengueres is strictly prohibited
Jose Berengueres
Berengueres |
Abstract
Project Background – CRM data from Etihad Airways was
analyzed. The data is three tables that comprise anonimized
information about passengers who enrolled the Etihad miles
program between 2006 and 2012. The tables contain data such
as: (1) Age and Nationality, etc. (2) Loyalty program purchases
etc. (Not used in this model) (3) Flight activity, miles earned etc.
The following pages explain what can be predicted by using the
data.
2
Berengueres |
Predicting if a new customer will become silver (high value) or not can
help concentrate the (limited) CRM resources on high potential customers.
To do this effectively accuracy is needed.
Using extrapolation is 50 % accuracy in predictions. Using new data mining techniques 82% can be achieved.
Gold%
Silver%
Basic%
30k%
50k%
Accumulated%%
miles%
7me%
Tier%
?"
3
Berengueres |
The D/S model can predict who will be high value with very high accuracy.
I am flying
Etihad for
first time!
D"days" S"days"
I can tell you if
she will become
Silver with 82%
accuracy
Silver"-er"
before""now"
I can tell you if
she will become
Silver with 50%
accuracy
4
Berengueres |
Example of an application that enhances the value of miles program:
optimal real-time upgrade allocation
Passenger Name Tier Status
Probability they
will become Silver
in X months
Wolfgang Amadeus Motzart Basic 0.99
Ludvig Van Beetoven Basic 0.97
Giuseppe Verdi Basic 0.89
Jean-Michel Jarre Basic 0.77
Yasuharu Konishi Basic 0.77
Maki Nomiya Basic 0.45
Teresa Teng Basic 0.42
Carl Philip Emanuel Bach Basic 0.41
Enric Granados Basic 0.00
Leonard Bernstein Basic 0.00
Carl Loewe Basic 0.00
Johan Strauss Basic 0.00
Isaac Albeniz Basic 0.00
George Gerschwin Basic 0.00
John Lenon Basic 0.00
John Williams Basic 0.00
5
Berengueres |
Evaluation of predictive power of D/S model (1/3)
Prediction*Model*with*3*months*of*data*&*lookout*1*months
Discovery*rate 82% of#future#Silver#where#identified#after#observ
False*Positive 3% 97%#of#predictions#are#correct#
Count*of*prediction prediction
Sivler*attain 0 1 Grand*Total
0 54752 37 54789
1 293 1309 1602
Grand*Total 55045 1346 56391
notes:#start#period#jul#1st#2012
of future Silver identified after observing them 3 months
97% of predictions are correct
6
Berengueres |
Evaluation of predictive power of D/S model (2/3)
id silver(attain prediction confidence miles d_miles s_miles
Prediction*Model*with*3*months*of*data*&*lookout*1*months
optimized
0011F8ED0AC8C8BB01508088620164121 1 95.8% 31727 31727 0
0043ADCD0AC8C8BB015080889C9B3D8C1 1 93.2% 26844 18419 8425
004E72260AC8C8BA00924088DED48EA21 1 95.4% 28154 24132 4022
005C87E60AC8C8BA009240888212E6551 1 93.5% 25818 6454 9682
0083BDAD0AC8C8BB015080889239B1A51 1 90.6% 44760 33570 0
00A8DBB00AC8C8B900A1808887E868951 1 96.6% 41008 41008 0
00FEEDB90AC8C8BB00820088B5AC162F1 0 9.8% 7261 7261 0
01037D1D0AC8C8BB015080888D445D2B1 0 2.9% 18420 7368 11052
0103DA960AC8C8BA00924088CBB007EC1 1 94.2% 29044 7261 7261
016DAB8D0AC8C8BA00924088D0CA81E21 1 93.3% 25422 25422 0
018A74C50AC8C8B900EE8088ABC59E931 0 44.2% 11830 1232 8134
018EF04D0AC8C8BA040B208536F2F5D41 1 94.9% 32870 21597 11273
01A0AA700AC8C8B900EE8088CB46716F1 1 96.1% 42616 21308 21308
01AE88820AC8C8BA040FC08553DEE5701 1 97.0% 42616 21308 21308
01B36BFB0AC8C8BB01508088F95FE4B81 0 4.5% 24314 7261 10201
01D040ED0AC8C8BB00820088113040551 1 94.4% 28716 28716 0
01F5A8220AC8C8BA00924088D75E0D1D1 0 3.9% 18626 9313 9313
0218F5CF0AC8C8BA01BE6088DF8970A21 1 95.1% 27790 27790 0
021C50910AC8C8BA01BE6088B1AF66B41 1 95.6% 27790 27790 0
7
Berengueres |
Evaluation of predictive power of D/S model (3/3)
id silver(attain prediction confidence miles d_miles s_miles
Prediction*Model*with*3*months*of*data*&*lookout*1*months
optimized
1D5478290AC8C884020C2C150404CC2F1 0 40.3% 0 0 0
2385D21B0AC8C8BB01E0A088BBC38CE01 0 7.6% 1855 0 0
297415D70AC8C8BB007D8088F5B405331 0 23.6% 7368 0 0
2A0781C60AC8C8BB007D8088A48FCD751 0 5.9% 3409 0 0
2C562D700AC8C8BB00ABA0883772D40C1 0 20.4% 3908 0 3908
3168DF040AC8C8BB00CC00883B12612B1 1 57.1% 0 0 0
3259FD070AC8C8B901C80088EF0F15681 0 0.6% 1500 0 750
571203D10AC8C8BB01F2608838F1235A1 0 0.2% 0 0 0
6FD9A3290AC8C8BB01D66088822420661 0 5.5% 0 0 0
75FBD22E0AC8C8BB00D87F95DCE5D7FD1 0 10.6% 1000 0 1000
76A280880AC8C8BB00D87F95A29BA62D1 0 0.3% 13925 0 13925
797B15940AC8C8BB005FA0321C1659B01 0 8.4% 1594 0 1594
7B58F52F0AC8C884045DF16DB2E7E8951 0 0.2% 2783 0 0
8893D36B0AC8C8BA00DA80888D7CC84C1 1 95.0% 27408 0 0
8E25ADB90AC8C8BB0036A088E65758641 0 5.9% 5756 0 5756
8E2F15A70AC8C8BB0036A0880E60BF591 0 43.2% 6946 0 6946
91B080AC0AC8C8BA03CE0085983E7A871 0 2.3% 21702 0 21702
94C3111B0AC8C8BB01438088FA43C1F51 0 12.0% 4660 0 0 case hard to
predict for humans
(ord miles desc)
8
Berengueres |
Evaluation of predictive power of D/S model not optimized case (1/4)
Prediction*Model*with*2*weeks*of*data*&*lookout*3*months
Discovery*rate 22% of#future#Silver#where#identified#after#observing#them#for#just#two#weeks
False*Positive 11% 87%#of#predictions#are#correct#<<>#new#marketing#opportunities
Count*of*prediction Prediction
Silver#Attained 0 1 Grand#Total
0 10682 8 10690
1 217 62 279
Grand*Total 10899 70 10969
thereshold 75%
Notes:#the#model#is#not#opJmized#for#this#
period#of#Jme.#Only#Flight#acJvity#and#
demographics#was#used.#No#data#from#
acJvity#table#was#used.#Values#depend#on#
thereshold.Chang#eand#refresh.#Will#update#
all#sheets.#Model#is#Not#
opJmized.Thereshold#vlaue#set#at#75%#to#
minimize#False#posiJves#
9
Berengueres |
Evaluation of predictive power of D/S model not optimized case (2/4)
id silver_attained predictionconfidence miles d_miles s_miles
09CABFBA0AC8C8B900D8C08863F7EA3C 0 1 0.985 27653 27653 16394
56C9887C0AC8C8BA005FE088ED47FFCF 0 0 0.015 24896 24896 0
296469DC0AC8C8BA007D00885EB18956 0 0 0.135 23696 23696 0
3771ED480AC8C8BB00CC0088BDE4C478 0 0 0.037 23370 23370 0
3D3137C10AC8C8B90076A088BB6EBB89 0 0 0.047 23034 23034 0
F1343CCE0AC8C8B900C0808816BD44C5 0 0 0.060 22857 22857 0
3F0378660AC8C8B90076A088CAE8C374 0 0 0.026 22768 22768 0
3794410A0AC8C8BA00AE20883E1652C4 0 0 0.017 22216 22216 0
AB0B85FC0AC8C8BB010B4088B6809697 0 0 0.295 21928 21928 0
E3FF02EE0AC8C8BA006E6088E43A076D 0 0 0.259 21784 21784 1855
1653EBF70AC8C8840491FD219EA21F75 0 0 0.103 21784 21784 0
3BF040EA0AC8C8BA0332E0851046F487 0 0 0.005 21554 21554 0
421552F70AC8C8BA012E0088F88B3F4E 0 0 0.503 21537 21537 0
Prediction2Model2with222weeks2of2data2&2lookout232months
not5optimized
Linear5extrapolaAon5
piBalls:5in5two5weeks5
23k5miles,5in5125more5
weeks5...?5
our5model5seldom5fails5
here.5
Linear extrapolation
pitfalls: in two weeks
23k miles, in 12
more weeks ...?
our model seldom
fails here.
10
Berengueres |
Evaluation of predictive power of D/S model not optimized case (3/4)
Threshold
Selected
id silver_attained predictionconfidence miles d_miles s_miles
Prediction5Model5with525weeks5of5data5&5lookout535months
not$optimized
6EABD2E40AC8C8BA0322808554F60797 1 1 99% 29369 15448 13921
69354F350AC8C884067B5BE2535913DE 1 1 99% 14042 14042 14042
3CF691C00AC8C8B90076A0884A9F9B23 1 1 99% 30024 30024 0
589B92470AC8C8B9032760850728D40D 1 1 99% 25614 10978 67112
C7F33DC20AC8C8B902F4C086FD407221 1 1 99% 28716 28716 21514
EABC93930AC8C8B900C08088B1962D24 1 1 98% 39208 19604 19604
D78D29E80AC8C8BA010F6088616214AB 1 1 98% 43028 43028 0
716E35F80AC8C8B901A7008844A4FF4B 1 1 98% 31560 15780 31560
32E79DFC0AC8C8BB00CC008857814D19 1 1 98% 26257 15389 15389
6B0AB9000AC8C8B90328C085C3CAE112 1 1 98% 31560 15780 31560
E16627680AC8C8B9012100884C61D367 1 1 97% 43660 21830 65490
243B8BDE0AC8C8BB00ABA088A4D3CEFD 1 1 97% 30978 15489 15489
750A14220AC8C883067781FE4BB3C6F3 1 1 96% 33570 16785 16785
ordered$by$
confidence$
11
Berengueres |
Evaluation of predictive power of D/S model not optimized case (4/4)
Threshold
Selected
id silver_attained predictionconfidence miles d_miles s_miles
Prediction5Model5with525weeks5of5data5&5lookout535months
not$optimized
E16627680AC8C8B9012100884C61D367 1 1 97% 43660 21830 65490
F78416DC0AC8C8BB01056088E52AE59F 1 1 79% 43660 21830 21830
F78BFDB60AC8C8B900FC6088B04ACF26 1 0 70% 43660 21830 21830
D78D29E80AC8C8BA010F6088616214AB 1 1 98% 43028 43028 0
AFD57B700AC8C8BA00868088358FDB7F 1 1 95% 43028 43028 0
EABC93930AC8C8B900C08088B1962D24 1 1 98% 39208 19604 19604
750A14220AC8C883067781FE4BB3C6F3 1 1 96% 33570 16785 16785
2C1B4FF40AC8C8BB00ABA088FF0A6B96 1 1 92% 32746 32746 0
C89F688F0AC8C8B900E460884156C145 1 1 91% 32746 32746 0
8B9896A50AC8C883045631A37038FF09 1 1 85% 32746 16373 16373
CD0C91060AC8C8BB0029E088D94C8A38 1 1 96% 31964 15982 15982
58F87A470AC8C8B904018085369AD47A 1 1 93% 31964 15982 15982
58ECEF6B0AC8C8B904018085F9EAAD0C 1 1 92% 31964 15982 15982
ordered$by$
miles$
accumulated$in$
2$weeks$
12

More Related Content

Viewers also liked

Sketch Thinking @ Vistaprint #AgileBarcelona
Sketch Thinking @ Vistaprint #AgileBarcelonaSketch Thinking @ Vistaprint #AgileBarcelona
Sketch Thinking @ Vistaprint #AgileBarcelonaJose Berengueres
 
The Role of Software Integration in Driving Successful Post-Sale Customer Eng...
The Role of Software Integration in Driving Successful Post-Sale Customer Eng...The Role of Software Integration in Driving Successful Post-Sale Customer Eng...
The Role of Software Integration in Driving Successful Post-Sale Customer Eng...Business Marketing Association (SoCal BMA)
 
Pob stage 2 marketing seminar 4 post students
Pob stage 2 marketing   seminar 4 post studentsPob stage 2 marketing   seminar 4 post students
Pob stage 2 marketing seminar 4 post studentsmoduledesign
 
Better managing your loyalty program - Improving your member experience: the ...
Better managing your loyalty program - Improving your member experience: the ...Better managing your loyalty program - Improving your member experience: the ...
Better managing your loyalty program - Improving your member experience: the ...Sergio Mello
 
[British Airways] 8 Persuasive Principle Used by British Airways to Boost the...
[British Airways] 8 Persuasive Principle Used by British Airways to Boost the...[British Airways] 8 Persuasive Principle Used by British Airways to Boost the...
[British Airways] 8 Persuasive Principle Used by British Airways to Boost the...Convertize
 
Airline marketing
Airline marketingAirline marketing
Airline marketingRohit Tomar
 
Jet airways digital strategy
Jet airways digital strategyJet airways digital strategy
Jet airways digital strategyAbhishek Gaurav
 
Etihad Fast facts & figures FEB 2016
Etihad Fast facts & figures FEB 2016Etihad Fast facts & figures FEB 2016
Etihad Fast facts & figures FEB 2016Y Consulting LLC
 
What is eCommerce
What is eCommerceWhat is eCommerce
What is eCommerceColin Lewis
 
Post-sale marketing deck for workshop- MYCyberSALE
Post-sale marketing deck for workshop- MYCyberSALE Post-sale marketing deck for workshop- MYCyberSALE
Post-sale marketing deck for workshop- MYCyberSALE SushiVid
 
Mapping the Business Model(Osterwalder Canvas) and Marketing Strategies of ET...
Mapping the Business Model(Osterwalder Canvas) and Marketing Strategies of ET...Mapping the Business Model(Osterwalder Canvas) and Marketing Strategies of ET...
Mapping the Business Model(Osterwalder Canvas) and Marketing Strategies of ET...Sarathy Kalaichelvan
 
Airline digital channels: Starting the conversation
Airline digital channels: Starting the conversationAirline digital channels: Starting the conversation
Airline digital channels: Starting the conversationmarc mcneill
 
The Value of Predictive Analytics and Decision Modeling
The Value of Predictive Analytics and Decision ModelingThe Value of Predictive Analytics and Decision Modeling
The Value of Predictive Analytics and Decision ModelingDecision Management Solutions
 
Leveraging Advanced Analytics to Drive Customer Behavior in the Airline Industry
Leveraging Advanced Analytics to Drive Customer Behavior in the Airline IndustryLeveraging Advanced Analytics to Drive Customer Behavior in the Airline Industry
Leveraging Advanced Analytics to Drive Customer Behavior in the Airline IndustryCognizant
 

Viewers also liked (18)

Sketch Thinking @ Vistaprint #AgileBarcelona
Sketch Thinking @ Vistaprint #AgileBarcelonaSketch Thinking @ Vistaprint #AgileBarcelona
Sketch Thinking @ Vistaprint #AgileBarcelona
 
How RISD became RISD
How RISD became RISDHow RISD became RISD
How RISD became RISD
 
Marketing communication presentation
Marketing communication presentationMarketing communication presentation
Marketing communication presentation
 
The Role of Software Integration in Driving Successful Post-Sale Customer Eng...
The Role of Software Integration in Driving Successful Post-Sale Customer Eng...The Role of Software Integration in Driving Successful Post-Sale Customer Eng...
The Role of Software Integration in Driving Successful Post-Sale Customer Eng...
 
Pob stage 2 marketing seminar 4 post students
Pob stage 2 marketing   seminar 4 post studentsPob stage 2 marketing   seminar 4 post students
Pob stage 2 marketing seminar 4 post students
 
Better managing your loyalty program - Improving your member experience: the ...
Better managing your loyalty program - Improving your member experience: the ...Better managing your loyalty program - Improving your member experience: the ...
Better managing your loyalty program - Improving your member experience: the ...
 
[British Airways] 8 Persuasive Principle Used by British Airways to Boost the...
[British Airways] 8 Persuasive Principle Used by British Airways to Boost the...[British Airways] 8 Persuasive Principle Used by British Airways to Boost the...
[British Airways] 8 Persuasive Principle Used by British Airways to Boost the...
 
Airline marketing
Airline marketingAirline marketing
Airline marketing
 
Jet airways digital strategy
Jet airways digital strategyJet airways digital strategy
Jet airways digital strategy
 
Etihad Fast facts & figures FEB 2016
Etihad Fast facts & figures FEB 2016Etihad Fast facts & figures FEB 2016
Etihad Fast facts & figures FEB 2016
 
Easyjet presentation
Easyjet presentationEasyjet presentation
Easyjet presentation
 
What is eCommerce
What is eCommerceWhat is eCommerce
What is eCommerce
 
Post-sale marketing deck for workshop- MYCyberSALE
Post-sale marketing deck for workshop- MYCyberSALE Post-sale marketing deck for workshop- MYCyberSALE
Post-sale marketing deck for workshop- MYCyberSALE
 
Mapping the Business Model(Osterwalder Canvas) and Marketing Strategies of ET...
Mapping the Business Model(Osterwalder Canvas) and Marketing Strategies of ET...Mapping the Business Model(Osterwalder Canvas) and Marketing Strategies of ET...
Mapping the Business Model(Osterwalder Canvas) and Marketing Strategies of ET...
 
Airline digital channels: Starting the conversation
Airline digital channels: Starting the conversationAirline digital channels: Starting the conversation
Airline digital channels: Starting the conversation
 
Airline Customer Value
Airline Customer Value Airline Customer Value
Airline Customer Value
 
The Value of Predictive Analytics and Decision Modeling
The Value of Predictive Analytics and Decision ModelingThe Value of Predictive Analytics and Decision Modeling
The Value of Predictive Analytics and Decision Modeling
 
Leveraging Advanced Analytics to Drive Customer Behavior in the Airline Industry
Leveraging Advanced Analytics to Drive Customer Behavior in the Airline IndustryLeveraging Advanced Analytics to Drive Customer Behavior in the Airline Industry
Leveraging Advanced Analytics to Drive Customer Behavior in the Airline Industry
 

Similar to Airline CRM big data opportunities

Melda Elmas-Project1-ppt.pptx
Melda Elmas-Project1-ppt.pptxMelda Elmas-Project1-ppt.pptx
Melda Elmas-Project1-ppt.pptxImelda903061
 
04.3 heterogeneous debt portfolios
04.3   heterogeneous debt portfolios04.3   heterogeneous debt portfolios
04.3 heterogeneous debt portfolioscrmbasel
 
Statistical Models for Proportional Outcomes
Statistical Models for Proportional OutcomesStatistical Models for Proportional Outcomes
Statistical Models for Proportional OutcomesWenSui Liu
 
CECL Methodology - CRE Loan Pools
CECL Methodology - CRE Loan PoolsCECL Methodology - CRE Loan Pools
CECL Methodology - CRE Loan PoolsLibby Bierman
 
Multi Objective Optimization of PMEDM Process Parameter by Topsis Method
Multi Objective Optimization of PMEDM Process Parameter by Topsis MethodMulti Objective Optimization of PMEDM Process Parameter by Topsis Method
Multi Objective Optimization of PMEDM Process Parameter by Topsis Methodijtsrd
 
11.3 credit default swaps
11.3   credit default swaps11.3   credit default swaps
11.3 credit default swapscrmbasel
 
Business statistics -_assignment_dec_2019_zf_sgc5ylme
Business statistics -_assignment_dec_2019_zf_sgc5ylmeBusiness statistics -_assignment_dec_2019_zf_sgc5ylme
Business statistics -_assignment_dec_2019_zf_sgc5ylmeAssignmentchimp
 
Business and Data Analytics Collaborative April Meetup
Business and Data Analytics Collaborative April MeetupBusiness and Data Analytics Collaborative April Meetup
Business and Data Analytics Collaborative April MeetupKen Tucker
 
07.3 credit ratings and fico scores
07.3   credit ratings and fico scores07.3   credit ratings and fico scores
07.3 credit ratings and fico scorescrmbasel
 
Maintaining Credit Quality in Banks and Credit Unions
Maintaining Credit Quality in Banks and Credit UnionsMaintaining Credit Quality in Banks and Credit Unions
Maintaining Credit Quality in Banks and Credit UnionsLibby Bierman
 
KDD capabilities 2016 v1.0
KDD capabilities 2016 v1.0KDD capabilities 2016 v1.0
KDD capabilities 2016 v1.0KDDanalytics
 
Credit risk scoring model final
Credit risk scoring model finalCredit risk scoring model final
Credit risk scoring model finalRitu Sarkar
 
Eric Ries leanstartup at Berkeley/Columbia
Eric Ries leanstartup at Berkeley/ColumbiaEric Ries leanstartup at Berkeley/Columbia
Eric Ries leanstartup at Berkeley/ColumbiaStanford University
 
Loan portfolio manufacturing sme's statistical analysis
Loan portfolio manufacturing sme's   statistical analysisLoan portfolio manufacturing sme's   statistical analysis
Loan portfolio manufacturing sme's statistical analysisManzar Ahmed
 
03.3 homogeneous debt portfolios
03.3   homogeneous debt portfolios03.3   homogeneous debt portfolios
03.3 homogeneous debt portfolioscrmbasel
 
Writing Sample
Writing SampleWriting Sample
Writing SampleYiqun Li
 

Similar to Airline CRM big data opportunities (20)

RMCPWSM_GCM_2015
RMCPWSM_GCM_2015RMCPWSM_GCM_2015
RMCPWSM_GCM_2015
 
Melda Elmas-Project1-ppt.pptx
Melda Elmas-Project1-ppt.pptxMelda Elmas-Project1-ppt.pptx
Melda Elmas-Project1-ppt.pptx
 
04.3 heterogeneous debt portfolios
04.3   heterogeneous debt portfolios04.3   heterogeneous debt portfolios
04.3 heterogeneous debt portfolios
 
Statistical Models for Proportional Outcomes
Statistical Models for Proportional OutcomesStatistical Models for Proportional Outcomes
Statistical Models for Proportional Outcomes
 
CECL Methodology - CRE Loan Pools
CECL Methodology - CRE Loan PoolsCECL Methodology - CRE Loan Pools
CECL Methodology - CRE Loan Pools
 
Credit Risk Model Building Steps
Credit Risk Model Building StepsCredit Risk Model Building Steps
Credit Risk Model Building Steps
 
Training Module
Training ModuleTraining Module
Training Module
 
Multi Objective Optimization of PMEDM Process Parameter by Topsis Method
Multi Objective Optimization of PMEDM Process Parameter by Topsis MethodMulti Objective Optimization of PMEDM Process Parameter by Topsis Method
Multi Objective Optimization of PMEDM Process Parameter by Topsis Method
 
11.3 credit default swaps
11.3   credit default swaps11.3   credit default swaps
11.3 credit default swaps
 
Business statistics -_assignment_dec_2019_zf_sgc5ylme
Business statistics -_assignment_dec_2019_zf_sgc5ylmeBusiness statistics -_assignment_dec_2019_zf_sgc5ylme
Business statistics -_assignment_dec_2019_zf_sgc5ylme
 
Business and Data Analytics Collaborative April Meetup
Business and Data Analytics Collaborative April MeetupBusiness and Data Analytics Collaborative April Meetup
Business and Data Analytics Collaborative April Meetup
 
07.3 credit ratings and fico scores
07.3   credit ratings and fico scores07.3   credit ratings and fico scores
07.3 credit ratings and fico scores
 
Maintaining Credit Quality in Banks and Credit Unions
Maintaining Credit Quality in Banks and Credit UnionsMaintaining Credit Quality in Banks and Credit Unions
Maintaining Credit Quality in Banks and Credit Unions
 
KDD capabilities 2016 v1.0
KDD capabilities 2016 v1.0KDD capabilities 2016 v1.0
KDD capabilities 2016 v1.0
 
Credit risk scoring model final
Credit risk scoring model finalCredit risk scoring model final
Credit risk scoring model final
 
Six sigma technique
Six sigma techniqueSix sigma technique
Six sigma technique
 
Eric Ries leanstartup at Berkeley/Columbia
Eric Ries leanstartup at Berkeley/ColumbiaEric Ries leanstartup at Berkeley/Columbia
Eric Ries leanstartup at Berkeley/Columbia
 
Loan portfolio manufacturing sme's statistical analysis
Loan portfolio manufacturing sme's   statistical analysisLoan portfolio manufacturing sme's   statistical analysis
Loan portfolio manufacturing sme's statistical analysis
 
03.3 homogeneous debt portfolios
03.3   homogeneous debt portfolios03.3   homogeneous debt portfolios
03.3 homogeneous debt portfolios
 
Writing Sample
Writing SampleWriting Sample
Writing Sample
 

More from Jose Berengueres

DF in the industrial Sector in ME_Mars Presentation_22June2023.pptx
DF in the industrial Sector in ME_Mars Presentation_22June2023.pptxDF in the industrial Sector in ME_Mars Presentation_22June2023.pptx
DF in the industrial Sector in ME_Mars Presentation_22June2023.pptxJose Berengueres
 
Euro tax on cloud computing misinformation
Euro tax on cloud computing misinformationEuro tax on cloud computing misinformation
Euro tax on cloud computing misinformationJose Berengueres
 
Coaching session for the Future Mindset Challenge slides
Coaching session for the Future Mindset Challenge slides Coaching session for the Future Mindset Challenge slides
Coaching session for the Future Mindset Challenge slides Jose Berengueres
 
Human Factors f berengueres sweb654_2021_sp
Human Factors f berengueres sweb654_2021_spHuman Factors f berengueres sweb654_2021_sp
Human Factors f berengueres sweb654_2021_spJose Berengueres
 
Gamification and growth hacking lecture 1 of 3
Gamification and growth hacking lecture 1 of 3Gamification and growth hacking lecture 1 of 3
Gamification and growth hacking lecture 1 of 3Jose Berengueres
 
The SIX RULES OF DATA VISUALIZATION
The SIX RULES OF DATA VISUALIZATIONThe SIX RULES OF DATA VISUALIZATION
The SIX RULES OF DATA VISUALIZATIONJose Berengueres
 
Data Visualization for Policy Decision Making (impulse talk)
Data Visualization for Policy Decision Making (impulse talk)Data Visualization for Policy Decision Making (impulse talk)
Data Visualization for Policy Decision Making (impulse talk)Jose Berengueres
 
DATA VISUALIZATION PRESENTATION AT ODS DUABI SEPTEMBER 2019
DATA VISUALIZATION PRESENTATION AT ODS DUABI SEPTEMBER 2019DATA VISUALIZATION PRESENTATION AT ODS DUABI SEPTEMBER 2019
DATA VISUALIZATION PRESENTATION AT ODS DUABI SEPTEMBER 2019Jose Berengueres
 
1 introduction to data visualization &amp; storytelling chapter 1 slides
1   introduction to data visualization &amp; storytelling  chapter 1 slides1   introduction to data visualization &amp; storytelling  chapter 1 slides
1 introduction to data visualization &amp; storytelling chapter 1 slidesJose Berengueres
 
Introduction to data visualization and storytelling - Chapter 1 slides
Introduction to data visualization and storytelling -  Chapter 1 slidesIntroduction to data visualization and storytelling -  Chapter 1 slides
Introduction to data visualization and storytelling - Chapter 1 slidesJose Berengueres
 
What is human centered design berengueres
What is  human centered design   berengueresWhat is  human centered design   berengueres
What is human centered design berengueresJose Berengueres
 
#Dgo2019 Conference workshop A3 - viza
#Dgo2019 Conference workshop A3 - viza#Dgo2019 Conference workshop A3 - viza
#Dgo2019 Conference workshop A3 - vizaJose Berengueres
 
Meetup creative design literature review by Kai Bruns 17 3-2019 2
Meetup creative design literature review by Kai Bruns 17 3-2019 2Meetup creative design literature review by Kai Bruns 17 3-2019 2
Meetup creative design literature review by Kai Bruns 17 3-2019 2Jose Berengueres
 
ikigai wheeloflife design for life
ikigai  wheeloflife design for life ikigai  wheeloflife design for life
ikigai wheeloflife design for life Jose Berengueres
 
IEEE Happiness an inside job asoman 2017
IEEE Happiness an inside job asoman 2017IEEE Happiness an inside job asoman 2017
IEEE Happiness an inside job asoman 2017Jose Berengueres
 
Palo alto design thinking meetup number 2
Palo alto design thinking meetup number 2Palo alto design thinking meetup number 2
Palo alto design thinking meetup number 2Jose Berengueres
 

More from Jose Berengueres (20)

DF in the industrial Sector in ME_Mars Presentation_22June2023.pptx
DF in the industrial Sector in ME_Mars Presentation_22June2023.pptxDF in the industrial Sector in ME_Mars Presentation_22June2023.pptx
DF in the industrial Sector in ME_Mars Presentation_22June2023.pptx
 
Euro tax on cloud computing misinformation
Euro tax on cloud computing misinformationEuro tax on cloud computing misinformation
Euro tax on cloud computing misinformation
 
Aaa
AaaAaa
Aaa
 
Coaching session for the Future Mindset Challenge slides
Coaching session for the Future Mindset Challenge slides Coaching session for the Future Mindset Challenge slides
Coaching session for the Future Mindset Challenge slides
 
Human Factors f berengueres sweb654_2021_sp
Human Factors f berengueres sweb654_2021_spHuman Factors f berengueres sweb654_2021_sp
Human Factors f berengueres sweb654_2021_sp
 
Gamification and growth hacking lecture 1 of 3
Gamification and growth hacking lecture 1 of 3Gamification and growth hacking lecture 1 of 3
Gamification and growth hacking lecture 1 of 3
 
The SIX RULES OF DATA VISUALIZATION
The SIX RULES OF DATA VISUALIZATIONThe SIX RULES OF DATA VISUALIZATION
The SIX RULES OF DATA VISUALIZATION
 
Data Visualization for Policy Decision Making (impulse talk)
Data Visualization for Policy Decision Making (impulse talk)Data Visualization for Policy Decision Making (impulse talk)
Data Visualization for Policy Decision Making (impulse talk)
 
DATA VISUALIZATION PRESENTATION AT ODS DUABI SEPTEMBER 2019
DATA VISUALIZATION PRESENTATION AT ODS DUABI SEPTEMBER 2019DATA VISUALIZATION PRESENTATION AT ODS DUABI SEPTEMBER 2019
DATA VISUALIZATION PRESENTATION AT ODS DUABI SEPTEMBER 2019
 
1 introduction to data visualization &amp; storytelling chapter 1 slides
1   introduction to data visualization &amp; storytelling  chapter 1 slides1   introduction to data visualization &amp; storytelling  chapter 1 slides
1 introduction to data visualization &amp; storytelling chapter 1 slides
 
Introduction to data visualization and storytelling - Chapter 1 slides
Introduction to data visualization and storytelling -  Chapter 1 slidesIntroduction to data visualization and storytelling -  Chapter 1 slides
Introduction to data visualization and storytelling - Chapter 1 slides
 
What is human centered design berengueres
What is  human centered design   berengueresWhat is  human centered design   berengueres
What is human centered design berengueres
 
#Dgo2019 Conference workshop A3 - viza
#Dgo2019 Conference workshop A3 - viza#Dgo2019 Conference workshop A3 - viza
#Dgo2019 Conference workshop A3 - viza
 
Meetup creative design literature review by Kai Bruns 17 3-2019 2
Meetup creative design literature review by Kai Bruns 17 3-2019 2Meetup creative design literature review by Kai Bruns 17 3-2019 2
Meetup creative design literature review by Kai Bruns 17 3-2019 2
 
ikigai wheeloflife design for life
ikigai  wheeloflife design for life ikigai  wheeloflife design for life
ikigai wheeloflife design for life
 
Data Visualization Tips
Data Visualization TipsData Visualization Tips
Data Visualization Tips
 
TIP Hannover Messe 2018
TIP Hannover Messe 2018TIP Hannover Messe 2018
TIP Hannover Messe 2018
 
Innovation event report
Innovation event reportInnovation event report
Innovation event report
 
IEEE Happiness an inside job asoman 2017
IEEE Happiness an inside job asoman 2017IEEE Happiness an inside job asoman 2017
IEEE Happiness an inside job asoman 2017
 
Palo alto design thinking meetup number 2
Palo alto design thinking meetup number 2Palo alto design thinking meetup number 2
Palo alto design thinking meetup number 2
 

Recently uploaded

133. Reviewer Certificate in Advances in Research
133. Reviewer Certificate in Advances in Research133. Reviewer Certificate in Advances in Research
133. Reviewer Certificate in Advances in ResearchManu Mitra
 
Day care leadership document it helps to a person who needs caring children
Day care leadership document it helps to a person who needs caring childrenDay care leadership document it helps to a person who needs caring children
Day care leadership document it helps to a person who needs caring childrenMeleseWolde3
 
0524.priorspeakingengagementslist-01.pdf
0524.priorspeakingengagementslist-01.pdf0524.priorspeakingengagementslist-01.pdf
0524.priorspeakingengagementslist-01.pdfThomas GIRARD BDes
 
Genaihelloallstudyjamheregetstartedwithai
GenaihelloallstudyjamheregetstartedwithaiGenaihelloallstudyjamheregetstartedwithai
Genaihelloallstudyjamheregetstartedwithaijoceko6768
 
કારકિર્દીના પંથે-2024 career guidance.pdf
કારકિર્દીના પંથે-2024 career guidance.pdfકારકિર્દીના પંથે-2024 career guidance.pdf
કારકિર્દીના પંથે-2024 career guidance.pdfSAIYEDASAD2
 
0524.THOMASGIRARD_SINGLEPAGERESUME-01.pdf
0524.THOMASGIRARD_SINGLEPAGERESUME-01.pdf0524.THOMASGIRARD_SINGLEPAGERESUME-01.pdf
0524.THOMASGIRARD_SINGLEPAGERESUME-01.pdfThomas GIRARD BDes
 
0524.THOMASGIRARD_CURRICULUMVITAE-01.pdf
0524.THOMASGIRARD_CURRICULUMVITAE-01.pdf0524.THOMASGIRARD_CURRICULUMVITAE-01.pdf
0524.THOMASGIRARD_CURRICULUMVITAE-01.pdfThomas GIRARD BDes
 
129. Reviewer Certificate in BioNature [2024]
129. Reviewer Certificate in BioNature [2024]129. Reviewer Certificate in BioNature [2024]
129. Reviewer Certificate in BioNature [2024]Manu Mitra
 
Part 1.pptx Part 1.pptx Part 1.pptx Part 1.pptx
Part 1.pptx Part 1.pptx Part 1.pptx Part 1.pptxPart 1.pptx Part 1.pptx Part 1.pptx Part 1.pptx
Part 1.pptx Part 1.pptx Part 1.pptx Part 1.pptxSheldon Byron
 
Widal Agglutination Test: A rapid serological diagnosis of typhoid fever
Widal Agglutination Test: A rapid serological diagnosis of typhoid feverWidal Agglutination Test: A rapid serological diagnosis of typhoid fever
Widal Agglutination Test: A rapid serological diagnosis of typhoid fevertaexnic
 
D.El.Ed. College List -Session 2024-26.pdf
D.El.Ed. College List -Session 2024-26.pdfD.El.Ed. College List -Session 2024-26.pdf
D.El.Ed. College List -Session 2024-26.pdfbipedoy339
 
Ralph - Project Presentation Enhancing System Security at Acme Flight Solutio...
Ralph - Project Presentation Enhancing System Security at Acme Flight Solutio...Ralph - Project Presentation Enhancing System Security at Acme Flight Solutio...
Ralph - Project Presentation Enhancing System Security at Acme Flight Solutio...MasterG
 
Guide to Physical Therapist Practice presentation
Guide to Physical Therapist Practice presentationGuide to Physical Therapist Practice presentation
Guide to Physical Therapist Practice presentationssuser00bcd3
 
5CL-ADBA,5cladba, the best supplier in China
5CL-ADBA,5cladba, the best supplier in China5CL-ADBA,5cladba, the best supplier in China
5CL-ADBA,5cladba, the best supplier in Chinaamy56318795
 
Master SEO in 2024 The Complete Beginner's Guide
Master SEO in 2024 The Complete Beginner's GuideMaster SEO in 2024 The Complete Beginner's Guide
Master SEO in 2024 The Complete Beginner's GuideTechEasifyInfotech
 

Recently uploaded (15)

133. Reviewer Certificate in Advances in Research
133. Reviewer Certificate in Advances in Research133. Reviewer Certificate in Advances in Research
133. Reviewer Certificate in Advances in Research
 
Day care leadership document it helps to a person who needs caring children
Day care leadership document it helps to a person who needs caring childrenDay care leadership document it helps to a person who needs caring children
Day care leadership document it helps to a person who needs caring children
 
0524.priorspeakingengagementslist-01.pdf
0524.priorspeakingengagementslist-01.pdf0524.priorspeakingengagementslist-01.pdf
0524.priorspeakingengagementslist-01.pdf
 
Genaihelloallstudyjamheregetstartedwithai
GenaihelloallstudyjamheregetstartedwithaiGenaihelloallstudyjamheregetstartedwithai
Genaihelloallstudyjamheregetstartedwithai
 
કારકિર્દીના પંથે-2024 career guidance.pdf
કારકિર્દીના પંથે-2024 career guidance.pdfકારકિર્દીના પંથે-2024 career guidance.pdf
કારકિર્દીના પંથે-2024 career guidance.pdf
 
0524.THOMASGIRARD_SINGLEPAGERESUME-01.pdf
0524.THOMASGIRARD_SINGLEPAGERESUME-01.pdf0524.THOMASGIRARD_SINGLEPAGERESUME-01.pdf
0524.THOMASGIRARD_SINGLEPAGERESUME-01.pdf
 
0524.THOMASGIRARD_CURRICULUMVITAE-01.pdf
0524.THOMASGIRARD_CURRICULUMVITAE-01.pdf0524.THOMASGIRARD_CURRICULUMVITAE-01.pdf
0524.THOMASGIRARD_CURRICULUMVITAE-01.pdf
 
129. Reviewer Certificate in BioNature [2024]
129. Reviewer Certificate in BioNature [2024]129. Reviewer Certificate in BioNature [2024]
129. Reviewer Certificate in BioNature [2024]
 
Part 1.pptx Part 1.pptx Part 1.pptx Part 1.pptx
Part 1.pptx Part 1.pptx Part 1.pptx Part 1.pptxPart 1.pptx Part 1.pptx Part 1.pptx Part 1.pptx
Part 1.pptx Part 1.pptx Part 1.pptx Part 1.pptx
 
Widal Agglutination Test: A rapid serological diagnosis of typhoid fever
Widal Agglutination Test: A rapid serological diagnosis of typhoid feverWidal Agglutination Test: A rapid serological diagnosis of typhoid fever
Widal Agglutination Test: A rapid serological diagnosis of typhoid fever
 
D.El.Ed. College List -Session 2024-26.pdf
D.El.Ed. College List -Session 2024-26.pdfD.El.Ed. College List -Session 2024-26.pdf
D.El.Ed. College List -Session 2024-26.pdf
 
Ralph - Project Presentation Enhancing System Security at Acme Flight Solutio...
Ralph - Project Presentation Enhancing System Security at Acme Flight Solutio...Ralph - Project Presentation Enhancing System Security at Acme Flight Solutio...
Ralph - Project Presentation Enhancing System Security at Acme Flight Solutio...
 
Guide to Physical Therapist Practice presentation
Guide to Physical Therapist Practice presentationGuide to Physical Therapist Practice presentation
Guide to Physical Therapist Practice presentation
 
5CL-ADBA,5cladba, the best supplier in China
5CL-ADBA,5cladba, the best supplier in China5CL-ADBA,5cladba, the best supplier in China
5CL-ADBA,5cladba, the best supplier in China
 
Master SEO in 2024 The Complete Beginner's Guide
Master SEO in 2024 The Complete Beginner's GuideMaster SEO in 2024 The Complete Beginner's Guide
Master SEO in 2024 The Complete Beginner's Guide
 

Airline CRM big data opportunities

  • 1. Berengueres Opportunities in Etihad miles program Review of findings UAEU study on loyalty program data February 2013 EB2013.02.28 CONFIDENTIAL AND PROPRIETARY Any use of this material without specific permission of Jose Berengueres is strictly prohibited Jose Berengueres
  • 2. Berengueres | Abstract Project Background – CRM data from Etihad Airways was analyzed. The data is three tables that comprise anonimized information about passengers who enrolled the Etihad miles program between 2006 and 2012. The tables contain data such as: (1) Age and Nationality, etc. (2) Loyalty program purchases etc. (Not used in this model) (3) Flight activity, miles earned etc. The following pages explain what can be predicted by using the data. 2
  • 3. Berengueres | Predicting if a new customer will become silver (high value) or not can help concentrate the (limited) CRM resources on high potential customers. To do this effectively accuracy is needed. Using extrapolation is 50 % accuracy in predictions. Using new data mining techniques 82% can be achieved. Gold% Silver% Basic% 30k% 50k% Accumulated%% miles% 7me% Tier% ?" 3
  • 4. Berengueres | The D/S model can predict who will be high value with very high accuracy. I am flying Etihad for first time! D"days" S"days" I can tell you if she will become Silver with 82% accuracy Silver"-er" before""now" I can tell you if she will become Silver with 50% accuracy 4
  • 5. Berengueres | Example of an application that enhances the value of miles program: optimal real-time upgrade allocation Passenger Name Tier Status Probability they will become Silver in X months Wolfgang Amadeus Motzart Basic 0.99 Ludvig Van Beetoven Basic 0.97 Giuseppe Verdi Basic 0.89 Jean-Michel Jarre Basic 0.77 Yasuharu Konishi Basic 0.77 Maki Nomiya Basic 0.45 Teresa Teng Basic 0.42 Carl Philip Emanuel Bach Basic 0.41 Enric Granados Basic 0.00 Leonard Bernstein Basic 0.00 Carl Loewe Basic 0.00 Johan Strauss Basic 0.00 Isaac Albeniz Basic 0.00 George Gerschwin Basic 0.00 John Lenon Basic 0.00 John Williams Basic 0.00 5
  • 6. Berengueres | Evaluation of predictive power of D/S model (1/3) Prediction*Model*with*3*months*of*data*&*lookout*1*months Discovery*rate 82% of#future#Silver#where#identified#after#observ False*Positive 3% 97%#of#predictions#are#correct# Count*of*prediction prediction Sivler*attain 0 1 Grand*Total 0 54752 37 54789 1 293 1309 1602 Grand*Total 55045 1346 56391 notes:#start#period#jul#1st#2012 of future Silver identified after observing them 3 months 97% of predictions are correct 6
  • 7. Berengueres | Evaluation of predictive power of D/S model (2/3) id silver(attain prediction confidence miles d_miles s_miles Prediction*Model*with*3*months*of*data*&*lookout*1*months optimized 0011F8ED0AC8C8BB01508088620164121 1 95.8% 31727 31727 0 0043ADCD0AC8C8BB015080889C9B3D8C1 1 93.2% 26844 18419 8425 004E72260AC8C8BA00924088DED48EA21 1 95.4% 28154 24132 4022 005C87E60AC8C8BA009240888212E6551 1 93.5% 25818 6454 9682 0083BDAD0AC8C8BB015080889239B1A51 1 90.6% 44760 33570 0 00A8DBB00AC8C8B900A1808887E868951 1 96.6% 41008 41008 0 00FEEDB90AC8C8BB00820088B5AC162F1 0 9.8% 7261 7261 0 01037D1D0AC8C8BB015080888D445D2B1 0 2.9% 18420 7368 11052 0103DA960AC8C8BA00924088CBB007EC1 1 94.2% 29044 7261 7261 016DAB8D0AC8C8BA00924088D0CA81E21 1 93.3% 25422 25422 0 018A74C50AC8C8B900EE8088ABC59E931 0 44.2% 11830 1232 8134 018EF04D0AC8C8BA040B208536F2F5D41 1 94.9% 32870 21597 11273 01A0AA700AC8C8B900EE8088CB46716F1 1 96.1% 42616 21308 21308 01AE88820AC8C8BA040FC08553DEE5701 1 97.0% 42616 21308 21308 01B36BFB0AC8C8BB01508088F95FE4B81 0 4.5% 24314 7261 10201 01D040ED0AC8C8BB00820088113040551 1 94.4% 28716 28716 0 01F5A8220AC8C8BA00924088D75E0D1D1 0 3.9% 18626 9313 9313 0218F5CF0AC8C8BA01BE6088DF8970A21 1 95.1% 27790 27790 0 021C50910AC8C8BA01BE6088B1AF66B41 1 95.6% 27790 27790 0 7
  • 8. Berengueres | Evaluation of predictive power of D/S model (3/3) id silver(attain prediction confidence miles d_miles s_miles Prediction*Model*with*3*months*of*data*&*lookout*1*months optimized 1D5478290AC8C884020C2C150404CC2F1 0 40.3% 0 0 0 2385D21B0AC8C8BB01E0A088BBC38CE01 0 7.6% 1855 0 0 297415D70AC8C8BB007D8088F5B405331 0 23.6% 7368 0 0 2A0781C60AC8C8BB007D8088A48FCD751 0 5.9% 3409 0 0 2C562D700AC8C8BB00ABA0883772D40C1 0 20.4% 3908 0 3908 3168DF040AC8C8BB00CC00883B12612B1 1 57.1% 0 0 0 3259FD070AC8C8B901C80088EF0F15681 0 0.6% 1500 0 750 571203D10AC8C8BB01F2608838F1235A1 0 0.2% 0 0 0 6FD9A3290AC8C8BB01D66088822420661 0 5.5% 0 0 0 75FBD22E0AC8C8BB00D87F95DCE5D7FD1 0 10.6% 1000 0 1000 76A280880AC8C8BB00D87F95A29BA62D1 0 0.3% 13925 0 13925 797B15940AC8C8BB005FA0321C1659B01 0 8.4% 1594 0 1594 7B58F52F0AC8C884045DF16DB2E7E8951 0 0.2% 2783 0 0 8893D36B0AC8C8BA00DA80888D7CC84C1 1 95.0% 27408 0 0 8E25ADB90AC8C8BB0036A088E65758641 0 5.9% 5756 0 5756 8E2F15A70AC8C8BB0036A0880E60BF591 0 43.2% 6946 0 6946 91B080AC0AC8C8BA03CE0085983E7A871 0 2.3% 21702 0 21702 94C3111B0AC8C8BB01438088FA43C1F51 0 12.0% 4660 0 0 case hard to predict for humans (ord miles desc) 8
  • 9. Berengueres | Evaluation of predictive power of D/S model not optimized case (1/4) Prediction*Model*with*2*weeks*of*data*&*lookout*3*months Discovery*rate 22% of#future#Silver#where#identified#after#observing#them#for#just#two#weeks False*Positive 11% 87%#of#predictions#are#correct#<<>#new#marketing#opportunities Count*of*prediction Prediction Silver#Attained 0 1 Grand#Total 0 10682 8 10690 1 217 62 279 Grand*Total 10899 70 10969 thereshold 75% Notes:#the#model#is#not#opJmized#for#this# period#of#Jme.#Only#Flight#acJvity#and# demographics#was#used.#No#data#from# acJvity#table#was#used.#Values#depend#on# thereshold.Chang#eand#refresh.#Will#update# all#sheets.#Model#is#Not# opJmized.Thereshold#vlaue#set#at#75%#to# minimize#False#posiJves# 9
  • 10. Berengueres | Evaluation of predictive power of D/S model not optimized case (2/4) id silver_attained predictionconfidence miles d_miles s_miles 09CABFBA0AC8C8B900D8C08863F7EA3C 0 1 0.985 27653 27653 16394 56C9887C0AC8C8BA005FE088ED47FFCF 0 0 0.015 24896 24896 0 296469DC0AC8C8BA007D00885EB18956 0 0 0.135 23696 23696 0 3771ED480AC8C8BB00CC0088BDE4C478 0 0 0.037 23370 23370 0 3D3137C10AC8C8B90076A088BB6EBB89 0 0 0.047 23034 23034 0 F1343CCE0AC8C8B900C0808816BD44C5 0 0 0.060 22857 22857 0 3F0378660AC8C8B90076A088CAE8C374 0 0 0.026 22768 22768 0 3794410A0AC8C8BA00AE20883E1652C4 0 0 0.017 22216 22216 0 AB0B85FC0AC8C8BB010B4088B6809697 0 0 0.295 21928 21928 0 E3FF02EE0AC8C8BA006E6088E43A076D 0 0 0.259 21784 21784 1855 1653EBF70AC8C8840491FD219EA21F75 0 0 0.103 21784 21784 0 3BF040EA0AC8C8BA0332E0851046F487 0 0 0.005 21554 21554 0 421552F70AC8C8BA012E0088F88B3F4E 0 0 0.503 21537 21537 0 Prediction2Model2with222weeks2of2data2&2lookout232months not5optimized Linear5extrapolaAon5 piBalls:5in5two5weeks5 23k5miles,5in5125more5 weeks5...?5 our5model5seldom5fails5 here.5 Linear extrapolation pitfalls: in two weeks 23k miles, in 12 more weeks ...? our model seldom fails here. 10
  • 11. Berengueres | Evaluation of predictive power of D/S model not optimized case (3/4) Threshold Selected id silver_attained predictionconfidence miles d_miles s_miles Prediction5Model5with525weeks5of5data5&5lookout535months not$optimized 6EABD2E40AC8C8BA0322808554F60797 1 1 99% 29369 15448 13921 69354F350AC8C884067B5BE2535913DE 1 1 99% 14042 14042 14042 3CF691C00AC8C8B90076A0884A9F9B23 1 1 99% 30024 30024 0 589B92470AC8C8B9032760850728D40D 1 1 99% 25614 10978 67112 C7F33DC20AC8C8B902F4C086FD407221 1 1 99% 28716 28716 21514 EABC93930AC8C8B900C08088B1962D24 1 1 98% 39208 19604 19604 D78D29E80AC8C8BA010F6088616214AB 1 1 98% 43028 43028 0 716E35F80AC8C8B901A7008844A4FF4B 1 1 98% 31560 15780 31560 32E79DFC0AC8C8BB00CC008857814D19 1 1 98% 26257 15389 15389 6B0AB9000AC8C8B90328C085C3CAE112 1 1 98% 31560 15780 31560 E16627680AC8C8B9012100884C61D367 1 1 97% 43660 21830 65490 243B8BDE0AC8C8BB00ABA088A4D3CEFD 1 1 97% 30978 15489 15489 750A14220AC8C883067781FE4BB3C6F3 1 1 96% 33570 16785 16785 ordered$by$ confidence$ 11
  • 12. Berengueres | Evaluation of predictive power of D/S model not optimized case (4/4) Threshold Selected id silver_attained predictionconfidence miles d_miles s_miles Prediction5Model5with525weeks5of5data5&5lookout535months not$optimized E16627680AC8C8B9012100884C61D367 1 1 97% 43660 21830 65490 F78416DC0AC8C8BB01056088E52AE59F 1 1 79% 43660 21830 21830 F78BFDB60AC8C8B900FC6088B04ACF26 1 0 70% 43660 21830 21830 D78D29E80AC8C8BA010F6088616214AB 1 1 98% 43028 43028 0 AFD57B700AC8C8BA00868088358FDB7F 1 1 95% 43028 43028 0 EABC93930AC8C8B900C08088B1962D24 1 1 98% 39208 19604 19604 750A14220AC8C883067781FE4BB3C6F3 1 1 96% 33570 16785 16785 2C1B4FF40AC8C8BB00ABA088FF0A6B96 1 1 92% 32746 32746 0 C89F688F0AC8C8B900E460884156C145 1 1 91% 32746 32746 0 8B9896A50AC8C883045631A37038FF09 1 1 85% 32746 16373 16373 CD0C91060AC8C8BB0029E088D94C8A38 1 1 96% 31964 15982 15982 58F87A470AC8C8B904018085369AD47A 1 1 93% 31964 15982 15982 58ECEF6B0AC8C8B904018085F9EAAD0C 1 1 92% 31964 15982 15982 ordered$by$ miles$ accumulated$in$ 2$weeks$ 12