SlideShare uma empresa Scribd logo
1 de 53
Ludo Longin
Direct Social Communications
Analytics in Fundraising
How knowing donors
helps in growing donors
Geert Verstraeten
Python Predictions
= communication agency
°1985
1 activity:
fundraising for humanitarian organisations
Team:
12 enthousiastic people
Direct Social Communications nv
Health Food
Belgium Belgian Assocation for Burn Injuries
Belgian Cystic Fibrosis Assocation
Kom op Tegen Kanker (Cancer Assoc.)
Food Banks
Restaurants of the Heart
World Mercy Ships
Chain of Hope
Damien Foundation
Medics Without Vacation
Children Animals
Belgium Collective Research and Expression
Youth Village
Pelicano Foundation
World If Child Help Veterinarians Without Borders
Handicap People
Belgium Blind Care Light & Love Flemish Autism Association
World Handicap International
Sensorial Handicap Cooperation
Pilots Without Borders
Mamas for Africa
The Voice of the Lebanese Women
Friends of Sister Emmanuelle
 ± 400 fundraising campaigns using dm
 > 8,000,000 letters to private individuals
 > 1,500,000 inserts in newspapers
> 600,000 donations per year
> 24,000,000 euros
Fundraising ≠ Easy Job
 Collecting-box
Many ways to raise money
for your organisation
 Collecting-Box
 Activity: pancakes, theatre, car wash,…
Many ways to raise money
for your organisation
 Collecting-Box
 Activity: pancakes, theatre, car wash,…
 Gala-Evening and Diner
Many ways to raise money
for your organisation
 Collecting-Box
 Activity: pancakes, theatre, car wash,…
 Gala-Evening and Diner
 Art Auction
Many ways to raise money
for your organisation
 Collecting-Box
 Activity: pancakes, theatre, car wash,…
 Gala-Evening and Diner
 Art Auction
 Face to face street fundraising
Many ways to raise money
for your organisation
 Collecting-Box
 Activity: pancakes, theatre, car wash,…
 Gala-Evening and Diner
 Art Auction
 Face to face street fundraising
 Telemarketing
Many ways to raise money
for your organisation
LABOUR INTENSIVE
One common element
 DRTV
Many ways to raise money
for your organisation
 Mobile giving
Many ways to raise money
for your organisation
 Mobile giving
Many ways to raise money
for your organisation
Most effective campaign:
American Red Cross – Haïti crisis
3 million unique donors sent an
sms for the earthquake in Haïti.
 32 million dollars
 Internet for fundraising?
◦ On line giving
◦ E-mail
◦ Social Networksites
Many ways to raise money
for your organisation
 Direct Mail
Many ways to raise money
for your organisation
 Easy to organise:
write – print - post
Advantages of Direct Mail
 Easy to organise:
write – print – post
 Easy to measure
Advantages of Direct Mail
 Easy to organise:
write – print – post
 Easy to measure
 Data Analysis/Segmentation improves results
Advantages of Direct Mail
 Female
 60+ years old
 religious
 Fully owned appartement/house
 Adult children have left the house
Typical dm-donor in Belgium
 Response rate in housemailing:
◦ 8 %
◦ 10 %
◦ 12 %
◦ 14 %
◦ More than 15 %
Normal results of dm-campaigns
Belgian Cystic Fibrosis Assocation
Housemailing:
- Posted on 20th april 2012
- 19.328 pieces sent
 4.881 donations received = 25,25 %
 Average donation = 30,90 euros
Belgian Cystic Fibrosis Assocation
Belgian Cystic Fibrosis Assocation
 Response rate in Acquisition campaigns:
◦ 2 %
◦ 2,5 %
◦ 3 %
◦ 4 or More %
Normal results of dm-campaigns
From test to roll-out
Test variation 1
Test variation 2
Test variation 3
Test Roll-out + New
tests
Roll-out (Test
variation 2)
Test variation 4
Test variation 5
Evaluation
Who ?
Target group
&
addresses
How / Means ?
Channels
What /Ask?
Content
How ?
Concept &
Creation
When ?
Timing &
frequency
Gadget ?
Incentive
Test
variables
# sent
units
# gifts
Total
Gifts €
Mean gift € %
Gift €/
sent unit
Cost €/
sent unit
Income €/
sent unit
8000 152 6438 42,36 1,90% 0,80 1,01 -0,21
8000 230 9501 41,31 2,88% 1,19 1,08 +0,11
Roll-out of 50.000 sent units:
5.500 euros profit in stead of 10.500 euros loss
Recruitment campaigns
Where do we get our donors from?
D.S.C.
± 220,000
addresses
CONSUDATA
+ criteria
6 million
addresses
Other
databases
Prospection Approaches
Address List Purchase
 Use of analytics: none
Prospection Approaches
Intuitive Segment Purchase / Hire
 Use of analytics: precooked segmentation
‘young
singles’
Informed Segment Purchase / Hire
 Use of analytics: precooked segmentation
Prospection Approaches
‘young
families’
Prospection Approaches
Customer/Donor Cloning
 Use of analytics: advanced (predictive models,
similarity models)
Python Predictions
Using all
available
data…
…we
predict
future
events …
…to
improve
decision
making
 Core business: Predictive Analytics
in marketing, risk and operations
 Core business: Predictive Analytics
 Since 2006
 SAS Partner since 2006
 References:
Python Predictions
Roadmap to Cloning
1
Define interesting donors
= donors ‘to be cloned’
2
Calculate Targets
= historic conversion rate per area
3
Calculate Predictors
= objective socio-demographic criteria per area
4
Predict future conversion
= Select & combine best predictors
5
Validate predictions
= Compare predicted vs real response, and profile
Project Approach
 Define which donors are used ‘to be cloned’
OPTION 1: Previous Blind Care Light & Love donors
OPTION 2: Previous DSC donors
BUT: only active donors selected =
at least minimal gift during last 2 years
1
Project Approach
2
 Per geographical area we know:
 # of donors
 # of households
 Historic conversion (# donors/ # households)
= ‘the target’
Project Approach
3
 We calculate socio-demographical information,
containing:
• Residents (age, education, activity,…)
• Housing (inhabitants, comfort,…)
• Neighbourhood (facilities, transport,…)
Around 700 variables known for each of the
20.000 geographical areas in Belgium
Project Approach
4
 We predict historic conversion:
Number of
Households
Age 55-
60y
270 10%
100 30%
65 70%
…
Cloning
Model
Predicted
Conversion
0.01%
0.02%
0.15%
…
Area
Number
Historic
Conversion
1 0%
2 0.05%
3 0.20%
… …
2 3 4
0%
1%
2%
3%
4%
5%
6%
7%
8%
9%
0-4 5-9 10-14 15-19 20-24 25-29 30-34 35-39 40-44 45-49 50-54 55-59 60-64 65-69 70-74 75-79 80-84 86-89 90-94 >95
Age category
Profile: Example
Households we
would not target
Households we
would target
5
Profile: Example
8%
26%
0 1 2 or more
Number of bathrooms
9%
21%
N/A < 35 m2 35 till
54 m2
55 till
84 m2
85 till
104 m2
105 till
124 m2
> 125
m2
House surface
Households we
would not target
Households we
would target
5
Estimated Quality
0.0%
0.5%
1.0%
1.5%
2.0%
2.5%
3.0%
3.5%
0 50000 100000 150000 200000 250000 300000
Cloning
Geo Segmentation
Age
 Comparison of historic response rate per target size
Number of Households Targeted
Response
Estimated Quality
0.0%
0.5%
1.0%
1.5%
2.0%
2.5%
3.0%
3.5%
0 50000 100000 150000 200000 250000 300000
Cloning
Geo Segmentation
Age
 Comparison of historic response rate per target size
Number of Households Targeted
Response
Estimated Quality
0.0%
0.5%
1.0%
1.5%
2.0%
2.5%
3.0%
3.5%
0 50000 100000 150000 200000 250000 300000
Cloning
Geo Segmentation
Age
 Comparison of historic response rate per target size
Number of Households Targeted
Response
Heatmap (predicted conversion)
 Example: Region of Bruges
Bruges
1.98%
2.29%
2.71%
Age > 55y Cloning
Top 100.000
Cloning
Top 10.000
Response Percentage
21.6 €
25.5 €
28.6 €
Age > 55y Cloning
Top 100.000
Cloning
Top 10.000
Average Donation Amount
improvement of 37% in
response rate
improvement of 32% in
donation amount
Real-life Prospection Campaign
0.43 €
0.58 €
0.78 €
Age > 55y Cloning
Top 100.000
Cloning
Top 10.000
Break
(revenue per letter sent)
improvement of 82% in
revenue per letter sent
 Current and
Future Usage
Real-life Prospection Campaign
QUESTIONS?
Or later?
Ludo Longin
ludo.longin@dsc.be
Tel +32 2 280 00 74
Direct Social Communications
www.dsc.be
Geert Verstraeten
geert.verstraeten@pythonpredictions.com
Tel +32 2 762 69 00
Python Predictions
www.pythonpredictions.com

Mais conteúdo relacionado

Destaque

Navigating the Security Landscape
Navigating the Security LandscapeNavigating the Security Landscape
Navigating the Security LandscapeSucuri
 
ระบบสารสนเทศเพื่อการตัดสินใจ
ระบบสารสนเทศเพื่อการตัดสินใจระบบสารสนเทศเพื่อการตัดสินใจ
ระบบสารสนเทศเพื่อการตัดสินใจPairaya Armradid
 
Exploring the Potential of Digital Lables
Exploring the Potential of Digital LablesExploring the Potential of Digital Lables
Exploring the Potential of Digital LablesClaire Bailey Ross
 
Sucuri Webinar: How to identify and clean a hacked Joomla! website
Sucuri Webinar: How to identify and clean a hacked Joomla! websiteSucuri Webinar: How to identify and clean a hacked Joomla! website
Sucuri Webinar: How to identify and clean a hacked Joomla! websiteSucuri
 
Uber and didi chuxing merger threatens traditional taxis
Uber and didi chuxing merger threatens traditional taxisUber and didi chuxing merger threatens traditional taxis
Uber and didi chuxing merger threatens traditional taxisKyna Tsai
 
Violin lessons for beginners
Violin lessons for beginnersViolin lessons for beginners
Violin lessons for beginnersRalph Conley
 
VIAJE, BALI,LOMBOK,JAVA,KARIMUNJAWA
VIAJE, BALI,LOMBOK,JAVA,KARIMUNJAWAVIAJE, BALI,LOMBOK,JAVA,KARIMUNJAWA
VIAJE, BALI,LOMBOK,JAVA,KARIMUNJAWAManueldv
 
Ulotka do katalogu Oriflame 10/2014
Ulotka do katalogu Oriflame 10/2014Ulotka do katalogu Oriflame 10/2014
Ulotka do katalogu Oriflame 10/2014Klara Resto
 
野村データ分析コンテスト完成版
野村データ分析コンテスト完成版野村データ分析コンテスト完成版
野村データ分析コンテスト完成版Shun Nakashio
 
6 - problem solving 1997 ppt
6  - problem solving 1997 ppt6  - problem solving 1997 ppt
6 - problem solving 1997 pptAnthony_Maiorano
 

Destaque (13)

Navigating the Security Landscape
Navigating the Security LandscapeNavigating the Security Landscape
Navigating the Security Landscape
 
ระบบสารสนเทศเพื่อการตัดสินใจ
ระบบสารสนเทศเพื่อการตัดสินใจระบบสารสนเทศเพื่อการตัดสินใจ
ระบบสารสนเทศเพื่อการตัดสินใจ
 
Exploring the Potential of Digital Lables
Exploring the Potential of Digital LablesExploring the Potential of Digital Lables
Exploring the Potential of Digital Lables
 
Sucuri Webinar: How to identify and clean a hacked Joomla! website
Sucuri Webinar: How to identify and clean a hacked Joomla! websiteSucuri Webinar: How to identify and clean a hacked Joomla! website
Sucuri Webinar: How to identify and clean a hacked Joomla! website
 
Uber and didi chuxing merger threatens traditional taxis
Uber and didi chuxing merger threatens traditional taxisUber and didi chuxing merger threatens traditional taxis
Uber and didi chuxing merger threatens traditional taxis
 
Violin lessons for beginners
Violin lessons for beginnersViolin lessons for beginners
Violin lessons for beginners
 
Non-Probability sampling
Non-Probability samplingNon-Probability sampling
Non-Probability sampling
 
Nonprobability Sampling
Nonprobability SamplingNonprobability Sampling
Nonprobability Sampling
 
VIAJE, BALI,LOMBOK,JAVA,KARIMUNJAWA
VIAJE, BALI,LOMBOK,JAVA,KARIMUNJAWAVIAJE, BALI,LOMBOK,JAVA,KARIMUNJAWA
VIAJE, BALI,LOMBOK,JAVA,KARIMUNJAWA
 
Ulotka do katalogu Oriflame 10/2014
Ulotka do katalogu Oriflame 10/2014Ulotka do katalogu Oriflame 10/2014
Ulotka do katalogu Oriflame 10/2014
 
野村データ分析コンテスト完成版
野村データ分析コンテスト完成版野村データ分析コンテスト完成版
野村データ分析コンテスト完成版
 
6 - problem solving 1997 ppt
6  - problem solving 1997 ppt6  - problem solving 1997 ppt
6 - problem solving 1997 ppt
 
7 - similar figures
7  - similar figures7  - similar figures
7 - similar figures
 

Semelhante a Predictive Analytics in Fundraising - Success Story DSC

Your one page guaranteed to work one page legacy plan f inal
Your one page guaranteed to work one page legacy plan f inalYour one page guaranteed to work one page legacy plan f inal
Your one page guaranteed to work one page legacy plan f inalWWF-Australia
 
Database Marketing in Fundraising
Database Marketing in FundraisingDatabase Marketing in Fundraising
Database Marketing in FundraisingBAQMaR
 
Financial alternatives starters day march 2016
Financial alternatives starters day march 2016Financial alternatives starters day march 2016
Financial alternatives starters day march 2016Securex
 
Digital donations meetup
Digital donations meetupDigital donations meetup
Digital donations meetupbetterplace-lab
 
Digital donations meetup
Digital donations meetupDigital donations meetup
Digital donations meetupbetterplace lab
 
Is fundraising the only game in town?
Is fundraising the only game in town?Is fundraising the only game in town?
Is fundraising the only game in town?walescva
 
Crowdfunding: going local or going global
Crowdfunding: going local or going globalCrowdfunding: going local or going global
Crowdfunding: going local or going globalClaire Ingram Bogusz
 
Matthew Sherrington - Save Port Meadow sustaining a campaign with no budget
Matthew Sherrington - Save Port Meadow sustaining a campaign with no budgetMatthew Sherrington - Save Port Meadow sustaining a campaign with no budget
Matthew Sherrington - Save Port Meadow sustaining a campaign with no budgetFairSay
 
Jürgen Ingels (B-Hive) #cfoconferenz
Jürgen Ingels (B-Hive) #cfoconferenzJürgen Ingels (B-Hive) #cfoconferenz
Jürgen Ingels (B-Hive) #cfoconferenzFDMagazine
 
OpenMarket & Open Fundraising at Mobile Marketing Live #mmliveglobal
OpenMarket & Open Fundraising at Mobile Marketing Live #mmliveglobalOpenMarket & Open Fundraising at Mobile Marketing Live #mmliveglobal
OpenMarket & Open Fundraising at Mobile Marketing Live #mmliveglobalOisin Lunny
 
The Next Women Innovation Summit at the 22nd of June in Amsterdam
The Next Women Innovation Summit at the 22nd of June in AmsterdamThe Next Women Innovation Summit at the 22nd of June in Amsterdam
The Next Women Innovation Summit at the 22nd of June in Amsterdamthenextwomen100
 
Researching and-shopping-online-in-belgium research-studies
Researching and-shopping-online-in-belgium research-studiesResearching and-shopping-online-in-belgium research-studies
Researching and-shopping-online-in-belgium research-studiesNicolas Finet
 
DONATEevents 19th may 2014 Institute of Fundraising
DONATEevents   19th may 2014 Institute of FundraisingDONATEevents   19th may 2014 Institute of Fundraising
DONATEevents 19th may 2014 Institute of Fundraisingwmakower
 
Dutch media landscape 2014 Q1 update by Starcom
Dutch media landscape 2014 Q1 update by StarcomDutch media landscape 2014 Q1 update by Starcom
Dutch media landscape 2014 Q1 update by StarcomstarcomNL
 
Bnsw events exeter welcome slide
Bnsw events exeter welcome slideBnsw events exeter welcome slide
Bnsw events exeter welcome slideSean Humby
 
Deutsche Fundraising Kongress - Segmentation
Deutsche Fundraising Kongress - SegmentationDeutsche Fundraising Kongress - Segmentation
Deutsche Fundraising Kongress - SegmentationPurple Vision
 
Crowdfunding - Sweden and Trends
Crowdfunding - Sweden and TrendsCrowdfunding - Sweden and Trends
Crowdfunding - Sweden and TrendsRobin Teigland
 

Semelhante a Predictive Analytics in Fundraising - Success Story DSC (20)

Your one page guaranteed to work one page legacy plan f inal
Your one page guaranteed to work one page legacy plan f inalYour one page guaranteed to work one page legacy plan f inal
Your one page guaranteed to work one page legacy plan f inal
 
Database Marketing in Fundraising
Database Marketing in FundraisingDatabase Marketing in Fundraising
Database Marketing in Fundraising
 
Financial alternatives starters day march 2016
Financial alternatives starters day march 2016Financial alternatives starters day march 2016
Financial alternatives starters day march 2016
 
Digital donations meetup
Digital donations meetupDigital donations meetup
Digital donations meetup
 
Digital donations meetup
Digital donations meetupDigital donations meetup
Digital donations meetup
 
Is fundraising the only game in town?
Is fundraising the only game in town?Is fundraising the only game in town?
Is fundraising the only game in town?
 
What's Next: The Annual
What's Next: The AnnualWhat's Next: The Annual
What's Next: The Annual
 
Crowdfunding: going local or going global
Crowdfunding: going local or going globalCrowdfunding: going local or going global
Crowdfunding: going local or going global
 
Matthew Sherrington - Save Port Meadow sustaining a campaign with no budget
Matthew Sherrington - Save Port Meadow sustaining a campaign with no budgetMatthew Sherrington - Save Port Meadow sustaining a campaign with no budget
Matthew Sherrington - Save Port Meadow sustaining a campaign with no budget
 
sdw gruenderforum
sdw gruenderforumsdw gruenderforum
sdw gruenderforum
 
Jürgen Ingels (B-Hive) #cfoconferenz
Jürgen Ingels (B-Hive) #cfoconferenzJürgen Ingels (B-Hive) #cfoconferenz
Jürgen Ingels (B-Hive) #cfoconferenz
 
OpenMarket & Open Fundraising at Mobile Marketing Live #mmliveglobal
OpenMarket & Open Fundraising at Mobile Marketing Live #mmliveglobalOpenMarket & Open Fundraising at Mobile Marketing Live #mmliveglobal
OpenMarket & Open Fundraising at Mobile Marketing Live #mmliveglobal
 
The Next Women Innovation Summit at the 22nd of June in Amsterdam
The Next Women Innovation Summit at the 22nd of June in AmsterdamThe Next Women Innovation Summit at the 22nd of June in Amsterdam
The Next Women Innovation Summit at the 22nd of June in Amsterdam
 
Researching and-shopping-online-in-belgium research-studies
Researching and-shopping-online-in-belgium research-studiesResearching and-shopping-online-in-belgium research-studies
Researching and-shopping-online-in-belgium research-studies
 
DONATEevents 19th may 2014 Institute of Fundraising
DONATEevents   19th may 2014 Institute of FundraisingDONATEevents   19th may 2014 Institute of Fundraising
DONATEevents 19th may 2014 Institute of Fundraising
 
Dutch media landscape 2014 Q1 update by Starcom
Dutch media landscape 2014 Q1 update by StarcomDutch media landscape 2014 Q1 update by Starcom
Dutch media landscape 2014 Q1 update by Starcom
 
Bnsw events exeter welcome slide
Bnsw events exeter welcome slideBnsw events exeter welcome slide
Bnsw events exeter welcome slide
 
Legacies
Legacies Legacies
Legacies
 
Deutsche Fundraising Kongress - Segmentation
Deutsche Fundraising Kongress - SegmentationDeutsche Fundraising Kongress - Segmentation
Deutsche Fundraising Kongress - Segmentation
 
Crowdfunding - Sweden and Trends
Crowdfunding - Sweden and TrendsCrowdfunding - Sweden and Trends
Crowdfunding - Sweden and Trends
 

Mais de Python Predictions

Long live customer segmentation at Delhaize
Long live customer segmentation at DelhaizeLong live customer segmentation at Delhaize
Long live customer segmentation at DelhaizePython Predictions
 
Can algorithms help to reduce absenteeism
Can algorithms help to reduce absenteeismCan algorithms help to reduce absenteeism
Can algorithms help to reduce absenteeismPython Predictions
 
Project definition workshop #disummit 2019
Project definition workshop #disummit 2019Project definition workshop #disummit 2019
Project definition workshop #disummit 2019Python Predictions
 
From a needs-based segmentation to customer relevancy
From a needs-based segmentation to customer relevancyFrom a needs-based segmentation to customer relevancy
From a needs-based segmentation to customer relevancyPython Predictions
 
The pivotal power of data science - Influencing the business model of a media...
The pivotal power of data science - Influencing the business model of a media...The pivotal power of data science - Influencing the business model of a media...
The pivotal power of data science - Influencing the business model of a media...Python Predictions
 
Data science explained in 10 applications
Data science explained in 10 applicationsData science explained in 10 applications
Data science explained in 10 applicationsPython Predictions
 
Teaser Lingerie Recommendations with Van de Velde - Data Innovation Summit 20...
Teaser Lingerie Recommendations with Van de Velde - Data Innovation Summit 20...Teaser Lingerie Recommendations with Van de Velde - Data Innovation Summit 20...
Teaser Lingerie Recommendations with Van de Velde - Data Innovation Summit 20...Python Predictions
 
Python Predictions: Core applications and services
Python Predictions: Core applications and servicesPython Predictions: Core applications and services
Python Predictions: Core applications and servicesPython Predictions
 
Python Predictions: Innovation
Python Predictions: InnovationPython Predictions: Innovation
Python Predictions: InnovationPython Predictions
 
Python Predictions: Training & Coaching offer
Python Predictions: Training & Coaching offerPython Predictions: Training & Coaching offer
Python Predictions: Training & Coaching offerPython Predictions
 
Managing Projects in Predictive Analytics
Managing Projects in Predictive AnalyticsManaging Projects in Predictive Analytics
Managing Projects in Predictive AnalyticsPython Predictions
 
Process mining - a case by ING Belgium and Python Predictions (update Oct 2016)
Process mining - a case by ING Belgium and Python Predictions (update Oct 2016)Process mining - a case by ING Belgium and Python Predictions (update Oct 2016)
Process mining - a case by ING Belgium and Python Predictions (update Oct 2016)Python Predictions
 
Predicting Customer Long Term Value at Eni Belgium
Predicting Customer Long Term Value at Eni BelgiumPredicting Customer Long Term Value at Eni Belgium
Predicting Customer Long Term Value at Eni BelgiumPython Predictions
 
Process mining - a case by ING Belgium and Python Predictions
Process mining - a case by ING Belgium and Python PredictionsProcess mining - a case by ING Belgium and Python Predictions
Process mining - a case by ING Belgium and Python PredictionsPython Predictions
 
Predictive analytics and data science at ING Belgium
Predictive analytics and data science at ING BelgiumPredictive analytics and data science at ING Belgium
Predictive analytics and data science at ING BelgiumPython Predictions
 
Winning with analytics - Data Innovation Summit 2015 - Made in Belgium
Winning with analytics - Data Innovation Summit 2015 - Made in BelgiumWinning with analytics - Data Innovation Summit 2015 - Made in Belgium
Winning with analytics - Data Innovation Summit 2015 - Made in BelgiumPython Predictions
 
Combining Logit and Ensemble Modeling for Increased Customer Churn Detection
Combining Logit and Ensemble Modeling  for Increased Customer Churn DetectionCombining Logit and Ensemble Modeling  for Increased Customer Churn Detection
Combining Logit and Ensemble Modeling for Increased Customer Churn DetectionPython Predictions
 

Mais de Python Predictions (19)

AI inspiration session in HR
AI inspiration session in HRAI inspiration session in HR
AI inspiration session in HR
 
Long live customer segmentation at Delhaize
Long live customer segmentation at DelhaizeLong live customer segmentation at Delhaize
Long live customer segmentation at Delhaize
 
Can algorithms help to reduce absenteeism
Can algorithms help to reduce absenteeismCan algorithms help to reduce absenteeism
Can algorithms help to reduce absenteeism
 
Project definition workshop #disummit 2019
Project definition workshop #disummit 2019Project definition workshop #disummit 2019
Project definition workshop #disummit 2019
 
From a needs-based segmentation to customer relevancy
From a needs-based segmentation to customer relevancyFrom a needs-based segmentation to customer relevancy
From a needs-based segmentation to customer relevancy
 
The pivotal power of data science - Influencing the business model of a media...
The pivotal power of data science - Influencing the business model of a media...The pivotal power of data science - Influencing the business model of a media...
The pivotal power of data science - Influencing the business model of a media...
 
Data science explained in 10 applications
Data science explained in 10 applicationsData science explained in 10 applications
Data science explained in 10 applications
 
Teaser Lingerie Recommendations with Van de Velde - Data Innovation Summit 20...
Teaser Lingerie Recommendations with Van de Velde - Data Innovation Summit 20...Teaser Lingerie Recommendations with Van de Velde - Data Innovation Summit 20...
Teaser Lingerie Recommendations with Van de Velde - Data Innovation Summit 20...
 
Python Predictions: Core applications and services
Python Predictions: Core applications and servicesPython Predictions: Core applications and services
Python Predictions: Core applications and services
 
Python Predictions: Innovation
Python Predictions: InnovationPython Predictions: Innovation
Python Predictions: Innovation
 
Python Predictions: Training & Coaching offer
Python Predictions: Training & Coaching offerPython Predictions: Training & Coaching offer
Python Predictions: Training & Coaching offer
 
Managing Projects in Predictive Analytics
Managing Projects in Predictive AnalyticsManaging Projects in Predictive Analytics
Managing Projects in Predictive Analytics
 
Predicting employee burnout
Predicting employee burnoutPredicting employee burnout
Predicting employee burnout
 
Process mining - a case by ING Belgium and Python Predictions (update Oct 2016)
Process mining - a case by ING Belgium and Python Predictions (update Oct 2016)Process mining - a case by ING Belgium and Python Predictions (update Oct 2016)
Process mining - a case by ING Belgium and Python Predictions (update Oct 2016)
 
Predicting Customer Long Term Value at Eni Belgium
Predicting Customer Long Term Value at Eni BelgiumPredicting Customer Long Term Value at Eni Belgium
Predicting Customer Long Term Value at Eni Belgium
 
Process mining - a case by ING Belgium and Python Predictions
Process mining - a case by ING Belgium and Python PredictionsProcess mining - a case by ING Belgium and Python Predictions
Process mining - a case by ING Belgium and Python Predictions
 
Predictive analytics and data science at ING Belgium
Predictive analytics and data science at ING BelgiumPredictive analytics and data science at ING Belgium
Predictive analytics and data science at ING Belgium
 
Winning with analytics - Data Innovation Summit 2015 - Made in Belgium
Winning with analytics - Data Innovation Summit 2015 - Made in BelgiumWinning with analytics - Data Innovation Summit 2015 - Made in Belgium
Winning with analytics - Data Innovation Summit 2015 - Made in Belgium
 
Combining Logit and Ensemble Modeling for Increased Customer Churn Detection
Combining Logit and Ensemble Modeling  for Increased Customer Churn DetectionCombining Logit and Ensemble Modeling  for Increased Customer Churn Detection
Combining Logit and Ensemble Modeling for Increased Customer Churn Detection
 

Último

joint cost.pptx COST ACCOUNTING Sixteenth Edition ...
joint cost.pptx  COST ACCOUNTING  Sixteenth Edition                          ...joint cost.pptx  COST ACCOUNTING  Sixteenth Edition                          ...
joint cost.pptx COST ACCOUNTING Sixteenth Edition ...NadhimTaha
 
Uneak White's Personal Brand Exploration Presentation
Uneak White's Personal Brand Exploration PresentationUneak White's Personal Brand Exploration Presentation
Uneak White's Personal Brand Exploration Presentationuneakwhite
 
Phases of Negotiation .pptx
 Phases of Negotiation .pptx Phases of Negotiation .pptx
Phases of Negotiation .pptxnandhinijagan9867
 
Falcon Invoice Discounting: The best investment platform in india for investors
Falcon Invoice Discounting: The best investment platform in india for investorsFalcon Invoice Discounting: The best investment platform in india for investors
Falcon Invoice Discounting: The best investment platform in india for investorsFalcon Invoice Discounting
 
Power point presentation on enterprise performance management
Power point presentation on enterprise performance managementPower point presentation on enterprise performance management
Power point presentation on enterprise performance managementVaishnaviGunji
 
Putting the SPARK into Virtual Training.pptx
Putting the SPARK into Virtual Training.pptxPutting the SPARK into Virtual Training.pptx
Putting the SPARK into Virtual Training.pptxCynthia Clay
 
Lundin Gold - Q1 2024 Conference Call Presentation (Revised)
Lundin Gold - Q1 2024 Conference Call Presentation (Revised)Lundin Gold - Q1 2024 Conference Call Presentation (Revised)
Lundin Gold - Q1 2024 Conference Call Presentation (Revised)Adnet Communications
 
Falcon's Invoice Discounting: Your Path to Prosperity
Falcon's Invoice Discounting: Your Path to ProsperityFalcon's Invoice Discounting: Your Path to Prosperity
Falcon's Invoice Discounting: Your Path to Prosperityhemanthkumar470700
 
Getting Real with AI - Columbus DAW - May 2024 - Nick Woo from AlignAI
Getting Real with AI - Columbus DAW - May 2024 - Nick Woo from AlignAIGetting Real with AI - Columbus DAW - May 2024 - Nick Woo from AlignAI
Getting Real with AI - Columbus DAW - May 2024 - Nick Woo from AlignAITim Wilson
 
The Abortion pills for sale in Qatar@Doha [+27737758557] []Deira Dubai Kuwait
The Abortion pills for sale in Qatar@Doha [+27737758557] []Deira Dubai KuwaitThe Abortion pills for sale in Qatar@Doha [+27737758557] []Deira Dubai Kuwait
The Abortion pills for sale in Qatar@Doha [+27737758557] []Deira Dubai Kuwaitdaisycvs
 
Cannabis Legalization World Map: 2024 Updated
Cannabis Legalization World Map: 2024 UpdatedCannabis Legalization World Map: 2024 Updated
Cannabis Legalization World Map: 2024 UpdatedCannaBusinessPlans
 
Mckinsey foundation level Handbook for Viewing
Mckinsey foundation level Handbook for ViewingMckinsey foundation level Handbook for Viewing
Mckinsey foundation level Handbook for ViewingNauman Safdar
 
Al Mizhar Dubai Escorts +971561403006 Escorts Service In Al Mizhar
Al Mizhar Dubai Escorts +971561403006 Escorts Service In Al MizharAl Mizhar Dubai Escorts +971561403006 Escorts Service In Al Mizhar
Al Mizhar Dubai Escorts +971561403006 Escorts Service In Al Mizharallensay1
 
Paradip CALL GIRL❤7091819311❤CALL GIRLS IN ESCORT SERVICE WE ARE PROVIDING
Paradip CALL GIRL❤7091819311❤CALL GIRLS IN ESCORT SERVICE WE ARE PROVIDINGParadip CALL GIRL❤7091819311❤CALL GIRLS IN ESCORT SERVICE WE ARE PROVIDING
Paradip CALL GIRL❤7091819311❤CALL GIRLS IN ESCORT SERVICE WE ARE PROVIDINGpr788182
 
Mifepristone Available in Muscat +918761049707^^ €€ Buy Abortion Pills in Oman
Mifepristone Available in Muscat +918761049707^^ €€ Buy Abortion Pills in OmanMifepristone Available in Muscat +918761049707^^ €€ Buy Abortion Pills in Oman
Mifepristone Available in Muscat +918761049707^^ €€ Buy Abortion Pills in Omaninstagramfab782445
 
TVB_The Vietnam Believer Newsletter_May 6th, 2024_ENVol. 006.pdf
TVB_The Vietnam Believer Newsletter_May 6th, 2024_ENVol. 006.pdfTVB_The Vietnam Believer Newsletter_May 6th, 2024_ENVol. 006.pdf
TVB_The Vietnam Believer Newsletter_May 6th, 2024_ENVol. 006.pdfbelieveminhh
 
Lucknow Housewife Escorts by Sexy Bhabhi Service 8250092165
Lucknow Housewife Escorts  by Sexy Bhabhi Service 8250092165Lucknow Housewife Escorts  by Sexy Bhabhi Service 8250092165
Lucknow Housewife Escorts by Sexy Bhabhi Service 8250092165meghakumariji156
 
Falcon Invoice Discounting: Aviate Your Cash Flow Challenges
Falcon Invoice Discounting: Aviate Your Cash Flow ChallengesFalcon Invoice Discounting: Aviate Your Cash Flow Challenges
Falcon Invoice Discounting: Aviate Your Cash Flow Challengeshemanthkumar470700
 

Último (20)

joint cost.pptx COST ACCOUNTING Sixteenth Edition ...
joint cost.pptx  COST ACCOUNTING  Sixteenth Edition                          ...joint cost.pptx  COST ACCOUNTING  Sixteenth Edition                          ...
joint cost.pptx COST ACCOUNTING Sixteenth Edition ...
 
Uneak White's Personal Brand Exploration Presentation
Uneak White's Personal Brand Exploration PresentationUneak White's Personal Brand Exploration Presentation
Uneak White's Personal Brand Exploration Presentation
 
HomeRoots Pitch Deck | Investor Insights | April 2024
HomeRoots Pitch Deck | Investor Insights | April 2024HomeRoots Pitch Deck | Investor Insights | April 2024
HomeRoots Pitch Deck | Investor Insights | April 2024
 
Phases of Negotiation .pptx
 Phases of Negotiation .pptx Phases of Negotiation .pptx
Phases of Negotiation .pptx
 
Falcon Invoice Discounting: The best investment platform in india for investors
Falcon Invoice Discounting: The best investment platform in india for investorsFalcon Invoice Discounting: The best investment platform in india for investors
Falcon Invoice Discounting: The best investment platform in india for investors
 
Power point presentation on enterprise performance management
Power point presentation on enterprise performance managementPower point presentation on enterprise performance management
Power point presentation on enterprise performance management
 
Putting the SPARK into Virtual Training.pptx
Putting the SPARK into Virtual Training.pptxPutting the SPARK into Virtual Training.pptx
Putting the SPARK into Virtual Training.pptx
 
Lundin Gold - Q1 2024 Conference Call Presentation (Revised)
Lundin Gold - Q1 2024 Conference Call Presentation (Revised)Lundin Gold - Q1 2024 Conference Call Presentation (Revised)
Lundin Gold - Q1 2024 Conference Call Presentation (Revised)
 
Falcon's Invoice Discounting: Your Path to Prosperity
Falcon's Invoice Discounting: Your Path to ProsperityFalcon's Invoice Discounting: Your Path to Prosperity
Falcon's Invoice Discounting: Your Path to Prosperity
 
Getting Real with AI - Columbus DAW - May 2024 - Nick Woo from AlignAI
Getting Real with AI - Columbus DAW - May 2024 - Nick Woo from AlignAIGetting Real with AI - Columbus DAW - May 2024 - Nick Woo from AlignAI
Getting Real with AI - Columbus DAW - May 2024 - Nick Woo from AlignAI
 
Buy gmail accounts.pdf buy Old Gmail Accounts
Buy gmail accounts.pdf buy Old Gmail AccountsBuy gmail accounts.pdf buy Old Gmail Accounts
Buy gmail accounts.pdf buy Old Gmail Accounts
 
The Abortion pills for sale in Qatar@Doha [+27737758557] []Deira Dubai Kuwait
The Abortion pills for sale in Qatar@Doha [+27737758557] []Deira Dubai KuwaitThe Abortion pills for sale in Qatar@Doha [+27737758557] []Deira Dubai Kuwait
The Abortion pills for sale in Qatar@Doha [+27737758557] []Deira Dubai Kuwait
 
Cannabis Legalization World Map: 2024 Updated
Cannabis Legalization World Map: 2024 UpdatedCannabis Legalization World Map: 2024 Updated
Cannabis Legalization World Map: 2024 Updated
 
Mckinsey foundation level Handbook for Viewing
Mckinsey foundation level Handbook for ViewingMckinsey foundation level Handbook for Viewing
Mckinsey foundation level Handbook for Viewing
 
Al Mizhar Dubai Escorts +971561403006 Escorts Service In Al Mizhar
Al Mizhar Dubai Escorts +971561403006 Escorts Service In Al MizharAl Mizhar Dubai Escorts +971561403006 Escorts Service In Al Mizhar
Al Mizhar Dubai Escorts +971561403006 Escorts Service In Al Mizhar
 
Paradip CALL GIRL❤7091819311❤CALL GIRLS IN ESCORT SERVICE WE ARE PROVIDING
Paradip CALL GIRL❤7091819311❤CALL GIRLS IN ESCORT SERVICE WE ARE PROVIDINGParadip CALL GIRL❤7091819311❤CALL GIRLS IN ESCORT SERVICE WE ARE PROVIDING
Paradip CALL GIRL❤7091819311❤CALL GIRLS IN ESCORT SERVICE WE ARE PROVIDING
 
Mifepristone Available in Muscat +918761049707^^ €€ Buy Abortion Pills in Oman
Mifepristone Available in Muscat +918761049707^^ €€ Buy Abortion Pills in OmanMifepristone Available in Muscat +918761049707^^ €€ Buy Abortion Pills in Oman
Mifepristone Available in Muscat +918761049707^^ €€ Buy Abortion Pills in Oman
 
TVB_The Vietnam Believer Newsletter_May 6th, 2024_ENVol. 006.pdf
TVB_The Vietnam Believer Newsletter_May 6th, 2024_ENVol. 006.pdfTVB_The Vietnam Believer Newsletter_May 6th, 2024_ENVol. 006.pdf
TVB_The Vietnam Believer Newsletter_May 6th, 2024_ENVol. 006.pdf
 
Lucknow Housewife Escorts by Sexy Bhabhi Service 8250092165
Lucknow Housewife Escorts  by Sexy Bhabhi Service 8250092165Lucknow Housewife Escorts  by Sexy Bhabhi Service 8250092165
Lucknow Housewife Escorts by Sexy Bhabhi Service 8250092165
 
Falcon Invoice Discounting: Aviate Your Cash Flow Challenges
Falcon Invoice Discounting: Aviate Your Cash Flow ChallengesFalcon Invoice Discounting: Aviate Your Cash Flow Challenges
Falcon Invoice Discounting: Aviate Your Cash Flow Challenges
 

Predictive Analytics in Fundraising - Success Story DSC

  • 1. Ludo Longin Direct Social Communications Analytics in Fundraising How knowing donors helps in growing donors Geert Verstraeten Python Predictions
  • 2. = communication agency °1985 1 activity: fundraising for humanitarian organisations Team: 12 enthousiastic people Direct Social Communications nv
  • 3. Health Food Belgium Belgian Assocation for Burn Injuries Belgian Cystic Fibrosis Assocation Kom op Tegen Kanker (Cancer Assoc.) Food Banks Restaurants of the Heart World Mercy Ships Chain of Hope Damien Foundation Medics Without Vacation
  • 4. Children Animals Belgium Collective Research and Expression Youth Village Pelicano Foundation World If Child Help Veterinarians Without Borders
  • 5. Handicap People Belgium Blind Care Light & Love Flemish Autism Association World Handicap International Sensorial Handicap Cooperation Pilots Without Borders Mamas for Africa The Voice of the Lebanese Women Friends of Sister Emmanuelle
  • 6.  ± 400 fundraising campaigns using dm  > 8,000,000 letters to private individuals  > 1,500,000 inserts in newspapers > 600,000 donations per year > 24,000,000 euros
  • 7.
  • 9.  Collecting-box Many ways to raise money for your organisation
  • 10.  Collecting-Box  Activity: pancakes, theatre, car wash,… Many ways to raise money for your organisation
  • 11.  Collecting-Box  Activity: pancakes, theatre, car wash,…  Gala-Evening and Diner Many ways to raise money for your organisation
  • 12.  Collecting-Box  Activity: pancakes, theatre, car wash,…  Gala-Evening and Diner  Art Auction Many ways to raise money for your organisation
  • 13.  Collecting-Box  Activity: pancakes, theatre, car wash,…  Gala-Evening and Diner  Art Auction  Face to face street fundraising Many ways to raise money for your organisation
  • 14.  Collecting-Box  Activity: pancakes, theatre, car wash,…  Gala-Evening and Diner  Art Auction  Face to face street fundraising  Telemarketing Many ways to raise money for your organisation
  • 16.  DRTV Many ways to raise money for your organisation
  • 17.  Mobile giving Many ways to raise money for your organisation
  • 18.  Mobile giving Many ways to raise money for your organisation Most effective campaign: American Red Cross – Haïti crisis 3 million unique donors sent an sms for the earthquake in Haïti.  32 million dollars
  • 19.  Internet for fundraising? ◦ On line giving ◦ E-mail ◦ Social Networksites Many ways to raise money for your organisation
  • 20.  Direct Mail Many ways to raise money for your organisation
  • 21.  Easy to organise: write – print - post Advantages of Direct Mail
  • 22.  Easy to organise: write – print – post  Easy to measure Advantages of Direct Mail
  • 23.  Easy to organise: write – print – post  Easy to measure  Data Analysis/Segmentation improves results Advantages of Direct Mail
  • 24.  Female  60+ years old  religious  Fully owned appartement/house  Adult children have left the house Typical dm-donor in Belgium
  • 25.  Response rate in housemailing: ◦ 8 % ◦ 10 % ◦ 12 % ◦ 14 % ◦ More than 15 % Normal results of dm-campaigns
  • 27. Housemailing: - Posted on 20th april 2012 - 19.328 pieces sent  4.881 donations received = 25,25 %  Average donation = 30,90 euros Belgian Cystic Fibrosis Assocation
  • 29.  Response rate in Acquisition campaigns: ◦ 2 % ◦ 2,5 % ◦ 3 % ◦ 4 or More % Normal results of dm-campaigns
  • 30. From test to roll-out Test variation 1 Test variation 2 Test variation 3 Test Roll-out + New tests Roll-out (Test variation 2) Test variation 4 Test variation 5 Evaluation
  • 31. Who ? Target group & addresses How / Means ? Channels What /Ask? Content How ? Concept & Creation When ? Timing & frequency Gadget ? Incentive Test variables
  • 32. # sent units # gifts Total Gifts € Mean gift € % Gift €/ sent unit Cost €/ sent unit Income €/ sent unit 8000 152 6438 42,36 1,90% 0,80 1,01 -0,21 8000 230 9501 41,31 2,88% 1,19 1,08 +0,11 Roll-out of 50.000 sent units: 5.500 euros profit in stead of 10.500 euros loss
  • 33. Recruitment campaigns Where do we get our donors from? D.S.C. ± 220,000 addresses CONSUDATA + criteria 6 million addresses Other databases
  • 34. Prospection Approaches Address List Purchase  Use of analytics: none
  • 35. Prospection Approaches Intuitive Segment Purchase / Hire  Use of analytics: precooked segmentation ‘young singles’
  • 36. Informed Segment Purchase / Hire  Use of analytics: precooked segmentation Prospection Approaches ‘young families’
  • 37. Prospection Approaches Customer/Donor Cloning  Use of analytics: advanced (predictive models, similarity models)
  • 38. Python Predictions Using all available data… …we predict future events … …to improve decision making  Core business: Predictive Analytics in marketing, risk and operations
  • 39.  Core business: Predictive Analytics  Since 2006  SAS Partner since 2006  References: Python Predictions
  • 40. Roadmap to Cloning 1 Define interesting donors = donors ‘to be cloned’ 2 Calculate Targets = historic conversion rate per area 3 Calculate Predictors = objective socio-demographic criteria per area 4 Predict future conversion = Select & combine best predictors 5 Validate predictions = Compare predicted vs real response, and profile
  • 41. Project Approach  Define which donors are used ‘to be cloned’ OPTION 1: Previous Blind Care Light & Love donors OPTION 2: Previous DSC donors BUT: only active donors selected = at least minimal gift during last 2 years 1
  • 42. Project Approach 2  Per geographical area we know:  # of donors  # of households  Historic conversion (# donors/ # households) = ‘the target’
  • 43. Project Approach 3  We calculate socio-demographical information, containing: • Residents (age, education, activity,…) • Housing (inhabitants, comfort,…) • Neighbourhood (facilities, transport,…) Around 700 variables known for each of the 20.000 geographical areas in Belgium
  • 44. Project Approach 4  We predict historic conversion: Number of Households Age 55- 60y 270 10% 100 30% 65 70% … Cloning Model Predicted Conversion 0.01% 0.02% 0.15% … Area Number Historic Conversion 1 0% 2 0.05% 3 0.20% … … 2 3 4
  • 45. 0% 1% 2% 3% 4% 5% 6% 7% 8% 9% 0-4 5-9 10-14 15-19 20-24 25-29 30-34 35-39 40-44 45-49 50-54 55-59 60-64 65-69 70-74 75-79 80-84 86-89 90-94 >95 Age category Profile: Example Households we would not target Households we would target 5
  • 46. Profile: Example 8% 26% 0 1 2 or more Number of bathrooms 9% 21% N/A < 35 m2 35 till 54 m2 55 till 84 m2 85 till 104 m2 105 till 124 m2 > 125 m2 House surface Households we would not target Households we would target 5
  • 47. Estimated Quality 0.0% 0.5% 1.0% 1.5% 2.0% 2.5% 3.0% 3.5% 0 50000 100000 150000 200000 250000 300000 Cloning Geo Segmentation Age  Comparison of historic response rate per target size Number of Households Targeted Response
  • 48. Estimated Quality 0.0% 0.5% 1.0% 1.5% 2.0% 2.5% 3.0% 3.5% 0 50000 100000 150000 200000 250000 300000 Cloning Geo Segmentation Age  Comparison of historic response rate per target size Number of Households Targeted Response
  • 49. Estimated Quality 0.0% 0.5% 1.0% 1.5% 2.0% 2.5% 3.0% 3.5% 0 50000 100000 150000 200000 250000 300000 Cloning Geo Segmentation Age  Comparison of historic response rate per target size Number of Households Targeted Response
  • 50. Heatmap (predicted conversion)  Example: Region of Bruges Bruges
  • 51. 1.98% 2.29% 2.71% Age > 55y Cloning Top 100.000 Cloning Top 10.000 Response Percentage 21.6 € 25.5 € 28.6 € Age > 55y Cloning Top 100.000 Cloning Top 10.000 Average Donation Amount improvement of 37% in response rate improvement of 32% in donation amount Real-life Prospection Campaign
  • 52. 0.43 € 0.58 € 0.78 € Age > 55y Cloning Top 100.000 Cloning Top 10.000 Break (revenue per letter sent) improvement of 82% in revenue per letter sent  Current and Future Usage Real-life Prospection Campaign
  • 53. QUESTIONS? Or later? Ludo Longin ludo.longin@dsc.be Tel +32 2 280 00 74 Direct Social Communications www.dsc.be Geert Verstraeten geert.verstraeten@pythonpredictions.com Tel +32 2 762 69 00 Python Predictions www.pythonpredictions.com