GET SOCIAL WITH US. #vision2016. Tweet, follow, share throughout the session.

Transcription

1 GET SOCIAL WITH US Tweet, follow, share throughout the session Experian Information Solutions, Inc. All rights reserved. 1

2 Profitable credit card lending to the underserved market: Bringing the underserved into the mainstream Experian and the marks used herein are service marks or registered trademarks of Experian Information Solutions, Inc. Other product and company names mentioned herein are the trademarks of their respective owners. No part of this copyrighted work may be reproduced, modified, or distributed in any form or manner without the prior written permission of Experian.

3 Introducing: Marla Blow Fenway Summer Michele Raneri Experian

4 Credit gives people a greater ability to weather shocks and take control of their finances. New York Times Magazine How Credit Card Debt Can Help the Poor February 16,

5 Subprime market analysis Michele Raneri 5

6 VantageScore 3.0 Model overview Predicts risk of borrower Likelihood of future serious delinquencies (90 days later or greater) Any type of account 24-month performance Score range of Higher scores represent a lower likelihood of risk Lower scores are higher risk A = Super-prime B = Prime C =Near prime D = Sub-prime F = Deep sub-prime

7 Subprime analysis What is the subprime bankcard landscape? How are you targeting subprime? Consumers with bankcards US: 170 million Subprime:16 million (9%) consumers Existing balances US: $671 billion Subprime $75 billion (11%) balances Average balances US: $3,954 per consumer Subprime: $4,807 per consumer Data Q Experian IntelliView SM ; Subprime defined VantageScore

8 Subprime analysis overview Dec 2013 Selected consumers VS3= , or not scoreable Dec 2014 Limit to consumer those who opened bankcard in 2014 Dec 2015 Pulled performance as of Dec 2015 ever 60DPD in 12 months Thick credit file >4 trades Thin credit file =<4 trades No trades VS3 = VantageScore 3.0 8

9 Credit metric comparison Distribution of consumer by file thickness 100% 90% 80% 70% 60% 50% 40% 30% 20% 10% 0% 11% No trades Thin (<=4) Thick (>=5) 58% 30% 29% 24% US Subprime 47% 9

10 VantageScore breakouts US vs. Subprime 70% Super Prime Prime Near Prime Sub-Prime Deep Subprime 60% 50% 40% 30% 20% 10% 0% US Average VantageScore 3.0: 667 Subprime Average VantageScore 3.0:

11 Credit metric comparison US vs. Subprime US Subprime $90 $85 $80 $75 $70 $84.4K $71.5K -15% $182 $180 $178 $176 $174 $180.9K $175.7K -3% $65 Total Balance $172 Mortgage Balance $20 $19 $18 $17 $16.9K $16.9K 0% $15 $10 $5 $5.2K $8.9K +73% $16 Auto Balance $- Bankcard Balance Subprime defined VantageScore 3.0: (from data sample) 11

12 Credit metric comparison US vs. Subprime Bankcard utilization rate US Subprime Average number of trades US Subprime 32% 75% Percent trades ever derog US Subprime Average VantageScore US Subprime 26% 42%

13 Improving decisioning VantageScore Income Insight SM Extended View SM Premier Attributes SM Predicts the likelihood of a consumer becoming 90 days delinquent or worse on any trade within 24-months Estimates the wage income of a consumer Credit score designed to assess the creditworthiness of underserved consumers who have limited or no credit history EVS Scored: 99% thins 91% no trades Comprehensive set of credit attributes updated perpetually which enable strategic and data driven decisions EVS = Extended View SM score 13

14 Predicting risk VantageScore Income Insight SM Extended View SM Premier Attributes SM CHAID analysis LOW likelihood of bad HIGH likelihood of bad Observation December 2013 Performance December 2015 Bad definition 60 DPD 14

15 Thick records (>4 trades) Probability 60+DPD 10.83% overall bad rate VS3: % Bad VS3: % Bad VS3: % Bad VS3: % Bad WE in 12 mo % Bad % Trade Derog % Bad % Trade Derog % Bad % Never Delinq 0-75% 13.79% Trades Satisfactory % % Never Delinq >75% 8.24% Trades Satisfactory >3 5.77% WE in 12 mo % Bad % Trade Derog % Bad % Trade Derog % Bad WE in 12 mo % Bad WE in 12 mo % Bad WE in 12 mo % Bad WE in 12 mo % Bad % Trade Derog % Bad % Trade Derog % Bad VS3 = VantageScore

16 Thick records (>4 trades) Probability 60+DPD Needle in the haystack 10.83% overall bad rate VS3: % Bad VS3: % Bad VS3: % Bad VS3: % Bad WE in 12 mo % Bad % Trade Derog % Bad % Trade Derog % Bad % Never Delinq 0-75% 13.79% % Never Delinq >75% 8.24% WE in 12 mo % Bad Trades Satisfactory % Keep records with 8.24% bad rate Below average bad rate Trades Satisfactory >3 5.77% % Trade Derog % Bad % Trade Derog % Bad WE in 12 mo % Bad WE in 12 mo % Bad WE in 12 mo % Bad WE in 12 mo % Bad % Trade Derog % Bad % Trade Derog % Bad VS3 = VantageScore

17 Thin records (<=4 trades) Probability 60+DPD 15.31% overall bad rate EVS: % EVS: % EVS: % EVS: % VS3: % Bad % Trades ever derog 0-50% 5.37% Bad VS3: % Bad % Trades ever derog % 14.56% Bad Trades Ever derog = % Bad Trades Ever derog = % Bad VS3 = VantageScore 3.0 EVS = Extended View SM score 17

18 Thin records (<=4 trades) Probability 60+DPD Manage to specific strategies 15.31% overall bad rate EVS: % EVS: % EVS: % EVS: % Extended View SM (EVS) rank orders really well, Can go a bit deeper using Premier Attributes SM VS3: % Bad VS3: % Bad % Trades ever derog 0-50% 5.37% Bad % Trades ever derog % 14.56% Bad Trades Ever derog = % Bad Trades Ever derog = % Bad VS3 = VantageScore

19 No trades Probability 60+DPD 12.34% overall bad rate EVS: % EVS: % EVS: % EVS: % # Inquiries % Bad # Inquiries % Bad # Inquiries > % Bad # Inquiries > % Bad EVS = Extended View SM score 19

20 No trades Probability 60+DPD 12.34% overall bad rate EVS: % EVS: % EVS: % EVS: % # Inquiries % Bad # Inquiries % Bad Even inquiries provide additional information # Inquiries > % Bad # Inquiries > % Bad EVS = Extended View SM score 20

21 Results interpretation Subprime study Utilizing a CHAID methodology provides options to segment populations for quick cuts Drill down to the most predictive risk segments using Premier Attributes SM such as: Total number of credit inquiries Worst ever status on a trade Percentage of trades ever derogatory Total number of open trades ever derogatory 21

22 FS Card case study Toby Shum 22

23 Subprime analysis overview Dec 2013 Selected records from a sample of FS Card marketing prospects (590,400) Dec 2014 Limit to consumer those who opened bankcard in 2014 Dec 2015 Pulled performance as of Dec 2015 ever 60DPD in 12mo. Thick credit file >4 trades Thin credit file <=4 trades No trades 23

24 VantageScore breakouts US vs. prospect file 70% Deep Subprime Sub-Prime Near Prime Prime Super Prime 60% 50% 40% 30% 20% 10% 0% US Average VantageScore 3.0: 665 Prospect Average VantageScore 3.0:

25 Prospect file detail Input population Thick 59.1% Thin 31.1% Collection inquiry only 6.2% No hit 3.6% EVS scored 98.7% EVS scored 97.8 % EVS scored 51.2% EVS exclusion 1.3% EVS exclusion 2.2% EVS exclusion 48.8% EVS = Extended View SM score *Complete list of exclusion definitions in appendix 25

26 Score matrix Prospect Thin population Thin File file VantageScore V3 Not Scoreable No Hit EVS Score Low Range High Range Not Scoreable 0.0% 0.1% 0.1% Deep Subprime 0.1% 13.1% 1.0% Sub Prime 0.5% 41.9% 15.6% Near Prime 0.3% 5.4% 15.4% Prime 0.1% 0.2% 6.3% Super Prime 0.0% 0.1% Total 0.9% 60.6% 38.4% EVS = Extended View SM score 26

27 Thin records (<=4 trades) Relative probability 60+DPD 104% 98% 87% Group average 73% EVS EVS Missing EVS EVS 700+ EVS = Extended View SM score 27

28 Thin records (<=4 trades) Relative probability 60+DPD 110% 104% 98% 92% 80% 79% Group average 67% EVS Missing , Income<$40k, Few Good Trades EVS 700+, Higher % Derog , Income<$40k, More Good Trades , Income>$40k EVS 700+, Lower % Derog EVS with additional variable overlays EVS = Extended View SM score 28

29 Score matrix Prospect No trades on file population Not Hit hit VantageScore V3 Not Scoreable No Hit EVS Score Low Range High Range Not Scoreable 21% 7.8% 39.2% Deep Subprime 2.3% 0.1% Sub Prime 0% 24.1% 5.0% Near Prime 0% 0.3% 0.2% Prime 0.0% 0.0% Super Prime 0.0% 0.0% Total 21% 35% 44% EVS = Extended View SM score 29

30 No trades Relative probability 60+DPD 108% 102% 98% Group average 79% EVS Missing EVS EVS EVS 700+ EVS = Extended View SM score 30

31 No trades Relative probability 60+DPD 108% 104% 100% Group average 83% 79% 75% EVS Missing , WE>40% w/dq , WE<40% EVS , Few DQ EVS = Extended View SM score 31

32 Results interpretation Prospect file Extended View SM score is an effective additional data source for thin records and no file segments Identifies additional lower risk marketing prospects Differentiate risk level within VantageScore ranges Can be further enhanced when used in combination with Premier Attributes SM 32

33 Summary on subprime 33

34 For additional information, please contact: Marla Blow Michele Raneri Follow us on 34

35 Share your thoughts about Vision 2016! Please take the time now to give us your feedback about this session. You can complete the survey in the mobile app or request a paper survey. Select the Survey 1 button and complete 2 Select the breakout session you attended 35

36