1
Collections, Predictive Analytics and Taxpayer Compliance
Management
John McCalden
McCalden Consulting
2
Agenda
• Some Collection Theory
• Decision Analytics
• Taxpayer Compliance Management
• Q & A
3
Percent of Cases Aging per Month (SC)
0%
20%
40%
60%
80%
100%
0 12 24 36 48 60
Age in Months
Per
cen
t
97 - 99
Source: South Carolina ARMS
4
Percent of Cases Aging per Month (SC)
y = 1.0489x-0.6291
R2 = 0.9988
0%
20%
40%
60%
80%
100%
0 12 24 36 48 60
Age in Months
Per
cen
t
97 - 99 Power (97 - 99)
5
Collection Rates,Based on Different Levels of Performance
0%
20%
40%
60%
80%
100%
0 12 24 36 48 60
Age in Months
Per
cen
t R
emai
nin
g
Forecast: -0.2 Forecast; -0.5 Forecast: -0.6291
Forecast: -1.0 Forecast: -2.0Forecast: -0.7
6
Effect of Raising the Level of Performance From -0.6291 to -0.7
0%
20%
40%
60%
80%
100%
0 12 24 36 48 60
Age in Months
Per
cen
t R
emai
nin
g
97 - 99 Forecast -0.7
y = 1x-0.7
R2 = 1
y = 1x-0.6291
R2 = 1
7
Average Balance by Age of Case
y = 390.49Ln(x) + 529.3R2 = 0.9334
$0
$500
$1,000
$1,500
$2,000
$2,500
0 12 24 36 48 60
Months
Ave
rag
e B
alan
ce (
$)
Average Per Case Log. (Average Per Case)
Source: South Carolina ARMS: Summary Receivables Report 12/31/2004
y = 390.49Ln(x) + 529.3R2 = 0.9334
8
Application of Aging Curve (-0.6291) and Average Balance Curve to a Hypothetical
Cohort of 10,000 Cases
Month
Aging Cases
Model 1Total $ Model 1
1 10000 $5,763,1003 5010 $4,963,7706 3239 $4,056,10012 2095 $3,171,34018 1623 $2,705,10524 1354 $2,403,70636 1049 $2,022,71248 876 $1,784,20160 761 $1,614,037
9
Percent of # and $ Collected, per Month of Aging
0%
20%
40%
60%
80%
100%
0 12 24 36 48 60
Age in Months
Per
cen
t C
olle
cted
% # Collected 1 % $ Collected 1
10
Comparison of Percent of # and $ Collected, per Month of Aging
0%
20%
40%
60%
80%
100%
0 12 24 36 48 60
Age in Months
Per
cen
t C
olle
cted
% # Collected 1 % $ Collected 1
% # Collected 2 % $ Collected 2
11
Hypothetical Improvement in Collections When Exponent Increases From
-0.6291 to -0.7
Month
Aging Cases
Model 1Total $ Model 1
Aging Cases
Model 2Total $ Model 2
# Difference
$ Difference
# Improvement
$ Improvement
1 10000 $5,763,100 10000 $5,763,100 0 $0 0.00% 0.00%3 5010 $4,963,770 4635 $4,592,230 375 $371,540 3.75% 6.45%6 3239 $4,056,100 2853 $3,572,724 386 $483,376 3.86% 8.39%12 2095 $3,171,340 1756 $2,658,173 339 $513,167 3.39% 8.90%18 1623 $2,705,105 1322 $2,203,419 301 $501,686 3.01% 8.71%24 1354 $2,403,706 1081 $1,919,059 273 $484,647 2.73% 8.41%36 1049 $2,022,712 814 $1,569,578 235 $453,134 2.35% 7.86%48 876 $1,784,201 665 $1,354,445 211 $429,756 2.11% 7.46%60 761 $1,614,037 569 $1,206,816 192 $407,221 1.92% 7.07%
12
How Do We Transition to a Higher Level of Performance?
0%
20%
40%
60%
80%
100%
0 12 24 36 48 60
Age in Months
Per
cen
t R
emai
nin
g
97 - 99 Forecast -0.7
y = 1x-0.7
R2 = 1
y = 1x-0.6291
R2 = 1
13
Use Decision Analytics!!
Use Information Intelligently to Make Business Decisions:
Optimize Collection Activity
Prioritize Audit Candidates
Supply Education to the Needy!
And Repeat
(Taxpayer Compliance Management Program!)
14
How Do We Use Information Intelligently?
• Forecast Performance (models)
• Appropriate Actions (decision strategies/treatment scenarios)
• Controlled Experiments (champion/challenger)
• Performance Reporting
15
Actual and Forecast 'Good' Probabilities for Repeat Filers (SC)
0%
20%
40%
60%
80%
100%
130 180 230 280 330 380 430 480 530
Score Range
'Go
od
' Pro
bab
ilit
y
0
1000
2000
3000
4000
5000
6000
7000
Actual Good Rate Forecast Good Rate N Cases
16
BUSINESS - Collections Decision Strategy (VA)
REASONCODE
BUSINESSCLASSCODE
DISTRICTOFFICE
ASSESSMENTS
BALANCE
RISK BALANCE
BUSINESS(existing)
LIENSOURCE
INDICATOR
FIELDAcceleratedTreatment
FLEA
BALANCE
No Action
High Value,Low Risk
BUSINESS(modified)
BEGIN
241
Other Other
Moderate
High
< $100
Yes
No
> = $100
< $1000
> = $1000
< $100
Lien after 60 days, then
$100-$1000 send to OCAs
$1000 + send to field
86
Low
> = $100
B=24133%
B-FLEA58%
B-NOACT75%
B-LOW63%
B-MOD61%
BUSINESS62%
B-CALL47%
B=FSD$45%
FilingFrequency
Field
X
B = X69%
=Data elements used to segment accounts
= Account groups for strategy implementation
Lien after 30 days, then
$100-$1000 send to OCAs
$1000 + send to field
53,523
576
179
3,914
623
30,242
5,062 2,057
10,288
582
17
Treatment Scenarios
• Allow low-risk cases to self-cure•
‘Accelerate’ high-risk cases to enforced collection actions
• Focus collector resource on medium-risk cases
• All scenarios end with enforced collection actions
18
Low-Risk Treatment Scenarios (SC)
Low Risk, Low Balance
PNOAReminder
LetterAssessment
20% Statement
Levy60 Days 60 Days45
Days
Lien
Low-BalanceHolding
OCA
Balance < $250
180 Days 10 yrs Purged
Day 1 Day 61 Day 121 Day 166 Day 186
Day 186
Day 186
Day 366+
20 Days
(No OpenLicense)
20 DaysOpen license
Balance > $250
20 DaysOpen license
Balance < $250
Balance > $250
Low Risk, High Balance
PNOAReminder
LetterAssessment
20% Statement
Call from Telecollections
Levy60 Days30
Days45
Days10
Days
Lien
Field
OCA180 Days 10 yrs Purged
Day 1 Day 61 Day 121 Day 166 Day 176 Day 196
Day 196
Day 196
Day 376+
20 Days
(No OpenLicense)
20 DaysOpen license
Call from Telecollections
30Days
19
Medium-Risk Treatment Scenarios (SC)
Medium Risk, Low Balance
PNOAReminder
LetterAssessment
20% Statement Levy40 Days 30 Days
30Days
Lien
Low-BalanceHolding
OCA
Balance < $250
180 Days 10 yrs Purged
Day 1 Day 41 Day 71 Day 121 Day 141
Day 141
Day 141
Day 321+
20 Days
(No OpenLicense)
20 DaysOpen license
Balance > $250
20 DaysOpen license
Balance < $250
Balance > $250
Call from Telecollections
Day 101
20Days
Medium Risk, High Balance
PNOACall from
TelecollectionsAssessment
20% Statement
Call from Telecollections Levy40 Days 30 Days
30Days
10Days
Lien
Field
OCA180 Days 10 yrs Purged
Day 1 Day 41 Day 71 Day 121 Day 131 Day 151
Day 151
Day 151
Day 331+
20 Days
(No OpenLicense)
20 DaysOpen license
Call from Telecollections
Day 101
20Days
20
High-Risk Treatment Scenarios (SC)
High Risk, Low Balance
PNOA Assessment20%
StatementLevy30 Days
20 Days
(No OpenLicense)
Lien
Low-BalanceHolding
OCA
Balance < $250
10 yrs Purged
Day 1 Day 31 Day 121Day 51
Day 51
Day 51
Day 231+
70 Days 110 Days
20 DaysOpen license
Balance > $250
20 DaysOpen license
Balance < $250
Balance > $250
High Risk, High Balance
PNOA Assessment20%
StatementLevy30 Days
20 Days
(No OpenLicense)
Lien
Field
OCA 10 yrs Purged
Day 1 Day 31 Day 121Day 51
Day 51
Day 51
Day 231+
70 Days 110 Days
20 DaysOpen license
Call from Telecollections
10Days
21
Treatment Scenarios in MA(Initial Design)
Treatment A
[Med. Risk](High Balance)
NOA Phone Auto-Research
Call & RP (trustee)
NOD FN & Call & RP Deem
Auto-LevyOpen or Assets
Field
FR Auto-Levy OCA
Treatment B
[High Risk](Low Balance)
Bus.
NOA Phone Auto-Research
NOD NIL Auto-LevyOpen or Assets
FR Auto-Levy OCA
Assign LIENFNCallRP
NOA Phone Auto-Research
NOD NIL Auto-LevyWageLevy
Wage Levy LIEN
CaseFR
LIENAuto-Levy OCA
CaseAssigned
Day1
Day30
Day45
Day61
Day90
Day97
Day105
Day111
Yes
No
Yes
No
Yes
No
Treatment C
[High Risk](High Balance)(Low Balance)
Ind.
Treatment D
[High Risk](High Balance)
Bus.
NOA Phone Auto-Research
NOD Open or Assets
FR Auto-Levy OCA
LIENFieldFNCall
Deem RP
Yes
No
CallRP-Propose
Day2
Day14
Treatment E
(Very High Balance)
Ind.
NOA Call
Assign
Treatment F
(Very High Balance)
Bus.
NOA Call
Assign
Low
Med
High
Low
Med
High
22
Champion-Challenger Evaluation
Primary Primary Challenger 1 Challenger 190% Grossed Up 10% Grossed Up
$ Available $450 $500 $50 $500
$ Collected $ 90 $100 $11 $110
Collection % 20% 20% 22% 22%
23
2004 State Tax Revenue
California 85,721 2,388 9 7.2 15 15,127 1
. .
. .
. .
Kentucky 8,463 2,041 21 7.7 9 1,493 23
Louisiana 8,026 1,777 34 6.8 24 1,416 24
Colorado 7,051 1,533 48 4.5 49 1,244 25
Alabama 7,018 1,549 46 5.9 42 1,238 26
South Carolina 6,804 1,621 43 6.3 34 1,201 27
Oklahoma 6,427 1,824 33 6.9 22 1,134 28
Oregon 6,103 1,698 40 6 41 1,077 29
Arkansas 5,581 2,027 23 8.4 8 985 30
Kansas 5,284 1,931 29 6.6 29 932 31
. .
. .
. .
South Dakota 1,063 1,378 49 4.8 47 188 50
U.S. Total 593,489 2,025 6.5 104,733
State
Total Taxes
($ million) Per Capita Rank
% of Pers.
Income RankTax Gap (15%)
($ million)Tax Gap
Rank
Source: FTA Web Site :- U.S. Bureau of the Census and Bureau of Economic Anaylsis.
24
Probability of Making an Assessment – PA Data
0.0
10.0
20.0
30.0
40.0
50.0
60.0
70.0
80.0
90.0
100.0
< 27
0
270
- 274
275
- 279
280
- 284
285
- 289
290
- 294
295
- 299
300
- 304
305
- 309
310
- 314
315
+
Score Range
Pro
bab
ility
ActualForecast
25
Sort Candidates by Cell and Probability (PA)
cum_Obs hours cum_yield myrank...3507 676851 196963641 3507 3508 677044 197019804 3508 3509 677237 197075967 3509 3510 677430 197132130 3510 3511 677623 197188293 3511 3512 677816 197244456 3512 3513 678009 197300619 3513 3514 678202 197356782 3514 3515 678395 197412945 3515...
26
Collection Action Transition Probabilities (Markov-Chain Analysis)
FTF
Notice
Assessment Payment
Plan
Levy Lien Field Visit Revoke Seize Responsible
Party
Cure
New 0.55 0.35 0.00
FTF Notice 0.00 0.70 0.10 0.20
Notice of Assessment 0.20
Assessment 0.20 0.20 0.05 0.25 0.30
Payment Plan 0.05 0.05 0.20 0.70
Levy 0.60
Lien 0.70
Field Visit 0.40
Revoke 0.10
Seize 0.50
Responsible Party 0.80
Fro
m
To
27
Probability of Curing by Age of CE and Type of Collection Action
1 3 6 12 18 24 36 48 60
New 0.10 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
FTF Notice 0.20 0.10 0.00 0.00 0.00 0.00 0.00 0.00 0.00
Notice of Assessment 0.10 0.10 0.05 0.00 0.00 0.00 0.00 0.00 0.00
Assessment 0.30 0.20 0.10 0.00 0.00 0.00 0.00 0.00 0.00
Payment Plan 0.70 0.80 0.70 0.60 0.50 0.30 0.20 0.10 0.10
Levy 0.60 0.70 0.70 0.60 0.60 0.40 0.40 0.30 0.20
Lien 0.10 0.60 6.00 0.60 0.50 0.40 0.30 0.30 0.30
Field Visit 0.40 0.40 0.50 0.50 0.50 0.30 0.30 0.20 0.20
Revoke 0.10 0.10 0.10 0.10 0.00 0.00 0.00 0.00 0.00
Seize 0.70 0.70 0.70 0.70 0.70 0.70 0.70 0.70 0.70
Responsible Party 0.80 0.80 0.80 0.80 0.80 0.80 0.80 0.80 0.80
Action Age (Months)
28
InboundInformationChannels
Customer/TaxpayerInformation Sources
Tax Processing
External Sources
•Customer Contact History•Billing History•Detailed Return Data•Payment History•Filing History & Methods•Other A/R History•Original Registration Data•Registration Status Updates
•Federal Return Data•RAR, CP2000 Fed Audits•Industry Trend Data•SIC Code Standards•Other States’ Tax Data•Credit Bureau Data•Other State Agency Data
TaxpayerInteractions
•Phone Calls•Letters•Returns
•E-File•Telefile•Internet•Imaged
•Payments•Electronic•Internet•Imaged
•Office Visits•Case ManagementContact Recording•Email•Federal DataSharing Programs•External Interfaces
RESPONSE TREATMENT
TAXPAYER COMPLIANCE MANAGEMENT
Decision Information
OutboundInformationChannels
•Phone Calls•Letters•Office Visits•WEB site•Email•Field Visits•Faxes•Mailings•Other?
Customer ContactDelivery Systems
Integrated Billing &Correspondence
Supporting Systems
Audit Caseload
Collections Caseload
Non-Filer Caseload
Education Caseload
Autodialer & IntelligentCall Management
Case Managementand Workflow
ComplianceStrategy Management
Compliance StrategyDecision Engine
IntegratedPreventative/Curative
Strategies
Decision Delivery
Decisions
Education S
trategy
Registration G
uidance
Com
pliance Initiatives
Collections S
trategy
Non-F
iler Strategy
Audit S
trategy
Challenger S
trategy
ComplianceReferral Generation
Compliance Management Initiatives
Reusable ReferralGeneration Utilities
Referrals
Under-reporters
Compliance initiatives
Non-Filers
Educational needs
Non-payers
ComplianceData Warehouse
Acquisition & Cleansing
Create/Add to Customer Profile
Data Mining
CustomerProfile
Database
Data Aggregation/Performance Summary
ExtractsEvents
PerformanceReporting
BehaviorModeling
PerformanceTables
Populate/Update
Data Access
Compliance ReferralQueue
InboundInformationChannels
Customer/TaxpayerInformation Sources
Tax Processing
External Sources
•Customer Contact History•Billing History•Detailed Return Data•Payment History•Filing History & Methods•Other A/R History•Original Registration Data•Registration Status Updates
•Federal Return Data•RAR, CP2000 Fed Audits•Industry Trend Data•SIC Code Standards•Other States’ Tax Data•Credit Bureau Data•Other State Agency Data
TaxpayerInteractions
•Phone Calls•Letters•Returns
•E-File•Telefile•Internet•Imaged
•Payments•Electronic•Internet•Imaged
•Office Visits•Case ManagementContact Recording•Email•Federal DataSharing Programs•External Interfaces
RESPONSE TREATMENT
TAXPAYER COMPLIANCE MANAGEMENT
Decision Information
OutboundInformationChannels
•Phone Calls•Letters•Office Visits•WEB site•Email•Field Visits•Faxes•Mailings•Other?
Customer ContactDelivery Systems
Integrated Billing &Correspondence
Supporting Systems
Audit Caseload
Collections Caseload
Non-Filer Caseload
Education Caseload
Autodialer & IntelligentCall Management
Case Managementand Workflow
ComplianceStrategy Management
Compliance StrategyDecision Engine
IntegratedPreventative/Curative
Strategies
Decision Delivery
Decisions
Education S
trategy
Registration G
uidance
Com
pliance Initiatives
Collections S
trategy
Non-F
iler Strategy
Audit S
trategy
Challenger S
trategy
Education S
trategy
Registration G
uidance
Com
pliance Initiatives
Collections S
trategy
Non-F
iler Strategy
Audit S
trategy
Challenger S
trategy
ComplianceReferral Generation
Compliance Management Initiatives
Reusable ReferralGeneration Utilities
Referrals
Under-reporters
Compliance initiatives
Non-Filers
Educational needs
Non-payers
ComplianceData Warehouse
Acquisition & Cleansing
Create/Add to Customer Profile
Data Mining
CustomerProfile
Database
Data Aggregation/Performance Summary
ExtractsEvents
PerformanceReporting
BehaviorModeling
PerformanceTables
Populate/UpdatePopulate/Update
Data Access
Compliance ReferralQueue