Differential Replication for Credit Scoring in Regulated Environments
Differential replication is a method to adapt existing machine learning solutions to the demands of highly regulated environments by reusing knowledge from one generation to the next. Copying is a technique that allows differential replication by projecting a given classifier onto a new hypothesis s...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-03-01
|
| Series: | Entropy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1099-4300/23/4/407 |
| _version_ | 1797539572721123328 |
|---|---|
| author | Irene Unceta Jordi Nin Oriol Pujol |
| author_facet | Irene Unceta Jordi Nin Oriol Pujol |
| author_sort | Irene Unceta |
| collection | DOAJ |
| description | Differential replication is a method to adapt existing machine learning solutions to the demands of highly regulated environments by reusing knowledge from one generation to the next. Copying is a technique that allows differential replication by projecting a given classifier onto a new hypothesis space, in circumstances where access to both the original solution and its training data is limited. The resulting model replicates the original decision behavior while displaying new features and characteristics. In this paper, we apply this approach to a use case in the context of credit scoring. We use a private residential mortgage default dataset. We show that differential replication through copying can be exploited to adapt a given solution to the changing demands of a constrained environment such as that of the financial market. In particular, we show how copying can be used to replicate the decision behavior not only of a model, but also of a full pipeline. As a result, we can ensure the decomposability of the attributes used to provide explanations for credit scoring models and reduce the time-to-market delivery of these solutions. |
| first_indexed | 2024-03-10T12:47:44Z |
| format | Article |
| id | doaj.art-bd87e7bc58b547909f304211f507ce11 |
| institution | Directory Open Access Journal |
| issn | 1099-4300 |
| language | English |
| last_indexed | 2024-03-10T12:47:44Z |
| publishDate | 2021-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Entropy |
| spelling | doaj.art-bd87e7bc58b547909f304211f507ce112023-11-21T13:22:14ZengMDPI AGEntropy1099-43002021-03-0123440710.3390/e23040407Differential Replication for Credit Scoring in Regulated EnvironmentsIrene Unceta0Jordi Nin1Oriol Pujol2BBVA Data & Analytics, 28050 Madrid, SpainESADE, Universitat Ramon Llull, 08172 Sant Cugat del Vallès, SpainDepartment of Mathematics and Computer Science, Universitat de Barcelona, 08007 Barcelona, SpainDifferential replication is a method to adapt existing machine learning solutions to the demands of highly regulated environments by reusing knowledge from one generation to the next. Copying is a technique that allows differential replication by projecting a given classifier onto a new hypothesis space, in circumstances where access to both the original solution and its training data is limited. The resulting model replicates the original decision behavior while displaying new features and characteristics. In this paper, we apply this approach to a use case in the context of credit scoring. We use a private residential mortgage default dataset. We show that differential replication through copying can be exploited to adapt a given solution to the changing demands of a constrained environment such as that of the financial market. In particular, we show how copying can be used to replicate the decision behavior not only of a model, but also of a full pipeline. As a result, we can ensure the decomposability of the attributes used to provide explanations for credit scoring models and reduce the time-to-market delivery of these solutions.https://www.mdpi.com/1099-4300/23/4/407differential replicationenvironmental adaptationcopyingcredit scoring |
| spellingShingle | Irene Unceta Jordi Nin Oriol Pujol Differential Replication for Credit Scoring in Regulated Environments Entropy differential replication environmental adaptation copying credit scoring |
| title | Differential Replication for Credit Scoring in Regulated Environments |
| title_full | Differential Replication for Credit Scoring in Regulated Environments |
| title_fullStr | Differential Replication for Credit Scoring in Regulated Environments |
| title_full_unstemmed | Differential Replication for Credit Scoring in Regulated Environments |
| title_short | Differential Replication for Credit Scoring in Regulated Environments |
| title_sort | differential replication for credit scoring in regulated environments |
| topic | differential replication environmental adaptation copying credit scoring |
| url | https://www.mdpi.com/1099-4300/23/4/407 |
| work_keys_str_mv | AT ireneunceta differentialreplicationforcreditscoringinregulatedenvironments AT jordinin differentialreplicationforcreditscoringinregulatedenvironments AT oriolpujol differentialreplicationforcreditscoringinregulatedenvironments |