Paper offers method for evaluating machine learning models
Bank of Spain paper looks at cost and benefits of ML models for predicting credit defaults
Regulators must make “significant efforts” to evaluate machine learning models used to predict credit defaults, according to a new paper published by the Bank of Spain.
Andrés Alonso and José Manuel Carbó find machine learning models “outperform” traditional models when predicting credit default, but only up to a certain point.
“More advanced ML models may offer gains in classification power of up to 20%,” the authors say. “As the algorithmic complexity increases, the gains in predictive
Only users who have a paid subscription or are part of a corporate subscription are able to print or copy content.
To access these options, along with all other subscription benefits, please contact info@centralbanking.com or view our subscription options here: http://subscriptions.centralbanking.com/subscribe
You are currently unable to print this content. Please contact info@centralbanking.com to find out more.
You are currently unable to copy this content. Please contact info@centralbanking.com to find out more.
Copyright Infopro Digital Limited. All rights reserved.
You may share this content using our article tools. Printing this content is for the sole use of the Authorised User (named subscriber), as outlined in our terms and conditions - https://www.infopro-insight.com/terms-conditions/insight-subscriptions/
If you would like to purchase additional rights please email info@centralbanking.com
Copyright Infopro Digital Limited. All rights reserved.
You may share this content using our article tools. Copying this content is for the sole use of the Authorised User (named subscriber), as outlined in our terms and conditions - https://www.infopro-insight.com/terms-conditions/insight-subscriptions/
If you would like to purchase additional rights please email info@centralbanking.com
More on Fintech
Bundesbank partners with MIT on digital euro privacy
EU previously raised concerns about single access point to verify holding limits
Carstens advances vision for future tokenised financial system
‘Finternet’ proposal envisages payments across linked unified ledgers
CBDCs could increase financial instability, Fed paper says
Central banks should consider price and quantity tools to mitigate risks, researchers say
MAS partners with Mastercard to tackle cyber risks
Singaporean central bank and payments firm will share information and conduct joint training
BIS and central banks develop AI tool to mine climate data
Hallucinations “do not seem” to impact results of initiative with Bank of Spain, ECB and Bundesbank
Fintech Benchmarks 2024 – model banks analysis
Data reveals how advanced and emerging economy central banks structure their fintech functions
HKMA launches next phase of CBDC pilot and sandbox
Hong Kong project will explore programmability, tokenisation and atomic settlement
Has mobile money achieved what retail CBDCs aspire to?
Central Banking Spring Meetings: Fintech panellists discuss financial inclusion and bank casualties
Most read
- ECB says iPhone is currently incompatible with digital euro
- Supervisors grapple with the smaller bank dilemma
- Central bank of the year: Central Bank of Brazil